Australian National University

Wenyi Pi

Neo4j APOC Library Use Case

 Author

Wenyi Pi (

 ORCID:

0009–0002–2884–277)

 Introduction

In the realm of Neo4j, the APOC (Awesome Procedures on Cypher) library stands as a powerful tool. Previously, We have talked about the importance of APOC in optimising Cypher queries and improving query efficiency in our article Exploring Methods of Cypher Query Optimisations.

Introduction to APOC: Enhancing Neo4j Capabilities

Xuzeng He

Latest findings in multiple research directions for handling graph prediction and optimization Author · Xuzeng He (

 ORCID:

0009–0005–7317–7426) A graph, in short, is a description of items linked by relations, where the items of a graph are called

 nodes

(or vertices) and their relations are called

 edges

(or links). Examples of graphs can include social networks (e.g. Instagram) or knowledge

Recent Advances in using Machine Learning with Graphs

Vaibhav Khobragade

Author: Vaibhav Khobragade (

 ORCID:

0009–0009–8807–5982) Introduction Large language models (LLMs) are becoming increasingly popular in natural language processing for their superior competence in various applications.

Enhancing Language Models: The Role of Knowledge Graph Augmentation in Overcoming LLM Challenges

Enhancing Data Interactivity with LLMs and Neo4j Knowledge Graphs Author Wenyi Pi (

 ORCID

: 0009–0002–2884–2771) Introduction Since OpenAI launched ChatGPT, a

 large language model (LLM)

based chatbot, in 2023, it has set off a technological wave.

The integration of large language models (LLMs) with Neo4j-based knowledge graphs

An Introduction to RA-CM3, MuRAG and RACE Author  Xuzeng He (ORCID: 0009-0005-7317-7426)  Generative Artificial Intelligence (GAI) has demonstrated impressive performances in tasks such as text generation and text-to-image generation.

Recent Advances in using Retrieving Multimodal Information for Augmented Generation

Amanda Kau

Unlocking the Power of Questions — A deep dive into Question Answering Systems

Author:

 Amanda Kau (ORCID:


 0009–0004–4949–9284


 )

Virtual assistants have popped up on numerous websites over the years.

Harnessing The Power of Knowledge Graphs in Question Answering

Qingqin Fang

An Introduction to Retrieval Augmented Generation (RAG) and Knowledge Graph

Author Qingqin Fang (ORCID: 0009–0003–5348–4264)

 Introduction

Large Language Models (LLMs) have transformed the landscape of natural language processing, demonstrating exceptional proficiency in generating text that closely resembles human language.

Hallucination in Large Language Models and Two Effective Alleviation Pathways

Yunzhong Zhang

Efficient creation of a stoplight report with data dashboard images

Author: Yunzhong Zhang (ORCID: 0009–0002–8177–419X) Comparing data dashboards is crucial for understanding trends and performance differences. Traditionally, this task required manual effort, which was slow and sometimes inaccurate. Now, thanks to OpenAI’s GPT-4 with Vision (GPT-4V), we are able to automate and improve this process.

How to use GPT-4V For Stoplight Report

Dhruv Gupta

Improving the performance of Large Language Models Author  Dhruv Gupta (ORCID: 0009-0004-7109-5403)  ChatGPT, which first came out in late 2022, took the world by storm. Since then, various LLM models and LLM based products such as Meta’s Llama and Google’s Gemini have emerged, demonstrating the power of LLMs.

RAG: The next big thing after LLMs?

Harvesting the Power and Knowledge of Large Language Models


 Author

Amanda Kau

 (ORCID:

0009–0004–4949–9284

 )

Introduction Knowledge Graphs are networks that represent data in a graphical format. The beauty of Knowledge Graphs lies in their representation of concepts, events and entities as nodes, and the relationships between them as edges.

Automated Knowledge Graph Construction with Large Language Models

Swinburne University of Technology

Nakul Nambiar

Zhuochen Wu

Authors:  Nakul Nambiar (ORCID: 0009-0009-9720-9233) Zhuochen Wu (ORCID: 0009-0000-5642-5348)  Research Graph is a structured representation of research objects that captures information about entities and the relationships between Researcher, Organisation, Publication, Grant and Research Data.

How to use GPT API to export a research graph from PDF publications

Dhruv Gupta

Prompt Engineering — Part 2


 Using intelligence to use artificial Intelligence: A deep dive into Prompt Engineering

Author Dhruv Gupta

 (ORCID:

0009–0004–7109–5403

 )

Introduction In the previous article we discussed what prompt engineering and some of the techniques used for prompt engineering.

Prompt Engineering — Part 2

Enhancing Open-Domain Conversational Question Answering with Knowledge-Enhanced Models and Knowledge Graphs


 How knowledge-enhanced language models and knowledge graphs are advancing open-domain conversational question answering

Author:

 Wenyi Pi (ORCID:


 0009-0002-2884-2771


 )

When searching for information on the website, it is common to come across a flood of

Enhancing Open-Domain Conversational Question Answering with Knowledge-Enhanced Models and…

Recent Advances in Using Machine Learning with Graphs — Part 2 Latest findings in multiple research directions for handling graph construction and network security issues Author · Xuzeng He (

 ORCID:

0009–0005–7317–7426) Introduction A graph, in short, is a description of items linked by relations, where the items of a graph are called nodes (or vertices) and their relations are called edges (or links). Examples of

Recent Advances in Using Machine Learning with Graphs — Part 2

Exploring AI’s Ethical Terrain: Addressing Bias, Security, and Beyond

Author: Vaibhav Khobragade (

 ORCID:

0009–0009–8807–5982) Large language models (LLMs) like OpenAI’s GPT-4, Meta’s LLaMA, and Google Gemini (previously called Bard) have showcased their vast capabilities, from passing bar exams and crafting articles to generating images and website code.

Ethics and AI: Confronting the Challenges Ahead

How to efficiently retrieve information for different applications

Author Wenyi Pi (ORCID: 0009-0002-2884-2771) This article aims to explore various ways in which Retrieval-Augmented Generation (RAG) can be utilised to retrieve information and generate responses effectively within the dialogue system. The rationale behind utilising RAG as well as potential ways in which it can be employed effectively will be covered.

Efficient Information Retrieval and Response Generation with Retrieval-Augmented Generation (RAG)

Amir Aryani

Authors  Nakul Nambiar (ORCID: 0009-0009-9720-9233) Amir Aryani (ORCID: 0000-0002-4259-9774)  Knowledge graphs, which offer a structured representation of data and its relationships, are revolutionising how we organise and access information.

Mini RAG using Neo4j

Aishwarya Nambissan

A novel approach to improving the efficiency of text search in graph databases utilizing Neo4j, OpenAI, and Typesense. Authors  Nakul Nambiar (ORCID: 0009–0009–9720–9233) Aishwarya Nambissan (ORCID: 0009–0003–3823–6609)  The ability to use cutting-edge tools and frameworks is essential for staying ahead in the ever-changing field of technology.

Typesense and Neo4j in a hybrid information retrieval solution

Amir Aryani

A brief overview of different types of clustering techniques and their algorithms. Authors Aishwarya Nambissan (ORCID: 0009-0003-3823-6609) Amir Aryani (ORCID: 0000-0002-4259-9774)

 Background

Clustering is a fascinating technique used in machine learning, where patterns or data points are grouped based on their similarities. It’s like finding hidden connections among different data points without predefined labels.

19 Clustering Techniques

Understanding the Evolutionary Journey of LLMs Author Wenyi Pi (

 ORCID

: 0009–0002–2884–2771) Introduction When we talk about large language models (LLMs), we are actually referring to a type of advanced software that can communicate in a human-like manner. These models have the amazing ability to understand complex contexts and generate content that is coherent and has a human feel.

Brief Introduction to the History of Large Language Models (LLMs)

Understanding Sequential Data Modelling with Keras for Time Series Prediction

 Author

Wenyi Pi (

 ORCID

: 0009–0002–2884–2771) Introduction Recurrent Neural Networks (RNNs) are a special type of neural networks that are suitable for learning representations of sequential data like text in Natural Language Processing (NLP). We will walk through a complete example of using RNNs for time series prediction, covering

Beginner’s Guide to Recurrent Neural Networks (RNNs) with Keras

Incorporating Knowledge Graphs to explain reasoning processes


 Author

Amanda Kau (

 ORCID:

0009–0004–4949–9284) Introduction Large language models (LLMs) like GPT-4 possess remarkable language abilities, allowing them to function as chatbots, translators, and much more.

Combining Knowledge Graphs With Language Models for Interpretability

Exploring the OpenAlex Data Structure and Visualization Author: Qingqin Fang (

 ORCID:

0009–0003–5348–4264)

 Introduction to OpenAlex

In today’s world, the realm of research papers is brimming with countless hot topics, and the sheer volume of publications can be overwhelming.

Unveiling Research Trends through OpenAlex Visualization

Large Language Models for Fake News Generation and Detection Author Amanda Kau (

 ORCID

: 0009–0004–4949–9284) Introduction In recent years, fake news has become an increasing concern for many, and for good reason. Newspapers, which we once trusted to deliver credible news through accountable journalists, are vanishing en masse along with their writers.

Are Large Language Models Our Allies or Enemies in the Fight Against Fake News?

Unlocking the power of language models: A deep dive into BERT


 Author:


 Dhruv Gupta (ORCID:


 0009–0004–7109–5403


 )

Clive Humby, in 2006 rightly said, “Data is the new oil”. With data being present everywhere, it has never been more valuable.

Language Models: Deep Dive into BERT

Attention mechanism not getting enough attention Author Dhruv Gupta (

 ORCID

: 0009–0004–7109–5403) Introduction As discussed in this article, RNNs were incapable of learning long-term dependencies. To solve this issue both LSTMs and GRUs were introduced. However, even though LSTMs and GRUs did a fairly decent job for textual data they did not perform well.

Transformers Models in NLP

Exploring the potentials and limitations of Vision Language Models

Author:

 Amanda Kau (ORCID:


 0009–0004–4949–9284


 )

The human brain is more extraordinary than any machine we could build. From an early age, many of us gain the ability to comprehend what our eyes tell us and articulate it. Furthermore, we combine evidence from all our senses to reason.

How Much Can Vision Language Models Really “See”?

A novel compression technique ensuring comparable performance with 70% less parameters

Author Amanda Kau (

 ORCID

: 0009–0004–4949–9284) Introduction The sizes of large language models (LLMs) have been steadily increasing over the last few years.

CompactifAI: Large Language Models Don’t Actually Have To Be Large

From Naive to Modular: Tracing the Evolution of Retrieval-Augmented Generation

Author · Vaibhav Khobragade (

 ORCID:

0009–0009–8807–5982) Introduction Large Language Models (LLMs) have achieved remarkable success.

Three Paradigms of RAG

An introduction to tools supporting PubMed Author: Xuzeng He (

 ORCID:

0009–0005–7317–7426) PubMed is a free Web literature search service developed and maintained by the National Center for Biotechnology Information (

 NCBI

), and it is also a part of NCBI’s Entrez retrieval system that provides access to a diverse set of 38 databases.

Enhancing PubMed: from a Medical Database to beyond

Aland Astudillo

How to use GROBID to extract text from PDF  Author  Aland Astudillo (ORCID: 0009-0008-8672-3168)  GROBID is a powerful and useful tool based on machine learning that can extract text information from PDF files and other files to a structured format. One of the key challenges in knowledge mining from academic articles is reading the content of PDF files.

How to use GROBID

Using Mistral for Data tagging Author · Xuzeng He (

 ORCID:

0009–0005–7317–7426) Introduction Data tagging, in simple terms, is the process of assigning labels or tags to your data so that they are easier to retrieve or analyse.

How to use Large Language Models to tag your data: A complete tutorial

Integrating temporal data into static knowledge graphs

 Author

Amanda Kau

 (ORCID:


 0009–0004–4949–9284


 )

Introduction Knowledge graphs (KGs) have proven to be an effective method of data representation that is increasingly popular. In KGs, entities and concepts are represented as nodes, while the relationships between nodes are depicted as edges.

Dynamic Knowledge Graphs: A Next Step For Data Representation?

Transformative Advances in Language Models through External Knowledge Integration

Author: Qingqin Fang (

 ORCID:

0009–0003–5348–4264)

 Introduction

In the dynamic field of natural language processing, the integration of external knowledge has emerged as a pivotal strategy for enhancing the performance of language models.

Deeper understanding of In-Context Retrieval-Augmented Language Models

Author  Amir Aryani (ORCID: 0000-0002-4259-9774) Introduction   In this article we look at Research Graph as an information model , and an approach to connect and capture the connections between research outputs, researchers and research activities. We explore the metadata model, and we discuss how to capture this graph in a Neo4j Graph Database.

Research Graph 101

Latest findings in multiple research directions for tackling reasoning and common sense challenges Author: Xuzeng He (

 ORCID:

0009–0005–7317–7426) Knowledge Graphs, such as Wikidata, contain rich relational information between entities and have been widely used as a structured format for storing and representing relational information.

Large Language Models and Knowledge Graphs: Ways to combine them

Using intelligence to use artificial Intelligence: A deep dive into Prompt Engineering


 Author


 Dhruv Gupta (ORCID:


 0009–0004–7109–5403


 )

Introduction Large Language Models (LLMs) have become the new normal in the field of Natural Language Processing (NLP). With their improved performance and generative power, people around the world are relying on it for

Prompt Engineering

Boosting Performance for Knowledge Graphs with Neo4j APOC Library

 Author

Wenyi Pi (ORCID: 0009–0002–2884–2771) Introduction A

 knowledge graph

(graph database) captures information about main entities in a domain and the relationships between them. It was an augmented feature store for connected data which gave access to compute, access and operationalise structure features.

Exploring Methods of Cypher Query Optimisations

The AI Helper Turning Mountains of Data into Bite-Sized Instructions

Author Aland Astudillo (ORCID: 0009-0008-8672-3168) LLMs have been changing the way the entire world deals with problems and day-by-day tasks. To make them better for specific applications, they need huge amounts of data and complex and expensive approaches to training them.

What is LLMLingua?

Refining AI Vision: How Retrieval-Augmented Generation Transforms Image Captioning in Large Language Models   Leveraging External Knowledge to Enhance the Descriptive Capabilities of AI Systems Author  Vaibhav Khobragade (ORCID: 0009–0009–8807–5982) Introduction   Large Language Models (LLMs) are artificial intelligence models that are trained on massive amounts of text data in order to generate human-like language and produce coherent

Refining AI Vision: How Retrieval-Augmented Generation Transforms Image Captioning in Large…

Tools and Platform for Integration of Knowledge Graph with RAG pipelines.

Authors Aland Astudillo (ORCID: 0009-0008-8672-3168) Aishwarya Nambissan (ORCID: 0009-0003-3823-6609) Many users of chatbots such as ChatGPT, have encountered the problem of receiving inappropriate or incompatible responses. There are several reasons why this might happen.

Unveiling the Synergy: Retrieval Augmented Generation (RAG) Meets Knowledge Graphs

Author  Amir Aryani: (ORCID: 0000-0002-4259-9774) Definition   A research collaboration network is a group of researchers, and practitioners, or both, working together on joint research activities. These networks often span across disciplines, geographic boundaries, and sectors, enabling participants to share resources, expertise, and data to address common research goals more effectively than they could individually.

Research Collaboration Network

Improving the performance and application of Large Language Models

Author Amanda Kau (ORCID: 0009-0004-4949-9284) Large language models (LLMs) like GPT-4, the engine of products like ChatGPT, have taken centre stage in recent years due to their astonishing capabilities. Yet, they are far from perfect.

Understanding Retrieval Pitfalls: Challenges Faced by Retrieval Augmented Generation (RAG) models

Exploring the Potential of Temporal Feature-Logic Embedding (TFLEX) in Complex Query Resolution

Author · Vaibhav Khobragade (

 ORCID:

0009–0009–8807–5982)

 Introduction

Artificial intelligence (AI) and knowledge representation in the field of temporal knowledge graphs are rapidly gaining interest.

Harnessing Temporal Dynamics: Advanced Reasoning using Temporal Knowledge Graphs

Exploring innovative Strategies in Combating Misinformation with Enhanced Multimodal Understanding Author Wenyi Pi (

 ORCID

: 0009–0002–2884–2771) Introduction Misinformation refers to false or inaccurate information that is often given to someone in a deliberate attempt to make them believe something that is not true. This has a significantly negative impact on public health, political stability and social trust and harmony.

Multimodal Large Language Models for Misinformation Detection and Reasoning

The Three Oldest Pillars of NLP

Author Dhruv Gupta (

 ORCID

: 0009–0004–7109–5403) Introduction Natural Language Processing (NLP) has almost become synonymous with Large Language Models (LLMs), Generative AI, and fancy chatbots. With the ever-increasing amount of textual data and exponential growth in computational knowledge, these models are improving every day.

RNNs vs GRUs vs LSTMs

A Unified and Collaborative Framework for LLM Author · Qingqin Fang (

 ORCID:

0009–0003–5348–4264) Introduction In today’s rapidly evolving field of artificial intelligence, large language models (LLMs) are demonstrating unprecedented potential. Particularly, the Retrieval-Augmented Generation (RAG) architecture has become a hot topic in AI technology due to its unique technical capabilities.

RAG 2.0 is Coming?

Bridging Human Perception and AI’s Future: The Convergence of Visual Understanding and Semantic Networks Author · Vaibhav Khobragade (

 ORCID:

0009–0009–8807–5982)

 Introduction

The fusion of Vision-Language Models (

 VLMs

), Generative Models, and Knowledge Graphs (

 KGs

) is reshaping how artificial intelligence (AI) understands and interacts with the world.

Tuning Vision-Language Models and Generative Models with Knowledge Graph

Understanding the Power and Applications of Natural Language Processing

 Author

Dhruv Gupta (

 ORCID:

0009–0004–7109–5403) Introduction We are living in the era of generative AI. In an era where you can ask AI models almost anything, they will most certainly have an answer to the query. With the increased computational power and the amount of textual data, these models are bound to improve their performance.

NLU vs. NLG: Unveiling the Two Sides of Natural Language Processing

Understanding how RNNs work and its applications


 Author

Wenyi Pi (

 ORCID

: 0009–0002–2884–2771) Introduction In the ever-evolving landscape of artificial intelligence (AI), bridging the gap between humans and machines has seen remarkable progress. Researchers and enthusiasts alike have tirelessly worked across numerous aspects of this field, bringing about amazing advancements.

An Introduction to Recurrent Neural Networks (RNNs)

Exploring the Boundaries of Creativity and Responsibility in the Age of AI-Driven Media

 Author

Vaibhav Khobragade (

 ORCID:

0009–0009–8807–5982)

 Introduction

In 2024, the discipline of Generative AI takes a big step forward with the launch of revolutionary models that convert text into dynamic films, altering the landscape of digital content creation.

Generative AI’s Leap into Video in 2024 and its Ethical Horizon

Addressing Misinformation, Bias, and Privacy Concerns

Author:

 Wenyi Pi (ORCID:


 0009–0002–2884–2771


 )

Recently, the spread of false or misinformation has become an important concern for people all over the world, especially in the era of big data and multimedia, where people are faced with a flood of information that makes it difficult to determine its authenticity.

The Ethical and Social Impact of Artificial Intelligence

Latest findings for the use of Knowledge Graph in the field of QA in multiple research directions Author: Xuzeng He (

 ORCID:

0009–0005–7317–7426) Question Answering (QA), the ability to interact with data using natural language questions and obtaining accurate results, has been a long-standing challenge in computer science dating back to the 1960s.

Question Answering enhanced by Knowledge Graph

Unlocking the power of knowledge graphs in research catalogues: A deep dive into OpenAlex


 Author:


 Dhruv Gupta (ORCID:


 0009–0004–7109–5403


 )

Clive Humby, in 2006 rightly said, “Data is the new oil”. With data being present everywhere, it has never been more valuable.

Knowledge Graphs: Deep Dive into OpenAlex

Techniques to integrate Knowledge Graphs into Language Models

 Author

Amanda Kau

 (ORCID:


 0009–0004–4949–9284


 )

Introduction Both knowledge graphs (KGs) and pre-trained language models (PLMs) have gained popularity due to their ability to comprehend world knowledge and their broad applicability.

A Deep Dive Into Knowledge Graph Enhanced Pre-trained Language Models

Automated Knowledge Graph Construction with Large Language Models — Part 2

 Harvesting the Power and Knowledge of Large Language Models

Author Amanda Kau (

 ORCID

:

 0009–0004–4949–9284

) Introduction Knowledge graphs (KGs) are a structured representation of data in a graphical format, in which entities are represented by nodes and are connected by edges representing relationships

Automated Knowledge Graph Construction with Large Language Models — Part 2

An improvement architecture superior to the Transformer, proposed by Meta Author · Qingqin Fang (

 ORCID:

0009–0003–5348–4264) Introduction Recently, researchers from Meta and the University of Southern California have introduced a model called Megalodon. They claim that this model can expand the context window of language models to handle millions of tokens without overwhelming your memory.

The longer the context, the better? Unlimited Context Length in Megalodon

Latest findings in pre-training graphs and using them for link recommendation Author · Xuzeng He (

 ORCID:

0009–0005–7317–7426) Introduction A graph, in short, is a description of items linked by relations, where the items of a graph are called nodes (or vertices) and their relations are called edges (or links). Examples of graphs can include social networks (e.g. Instagram) or knowledge graphs (e.g. Wikipedia). In Instagram

Working with Graphs: Pre-training and Application

Unlocking the Future of AI: The Transformative Journey of Large Language Models Author · Vaibhav Khobragade (

 ORCID:

0009–0009–8807–5982)

 Introduction

Human language development is innate and evolves throughout life. Machines lack this ability to evolve without advanced AI algorithms.

The Journey of Large Language Models: Evolution, Application, and Limitations

Understanding Knowledge Networks From A Graph Perspective


 Author:


 Amanda Kau (ORCID:


 0009–0004–4949–9284


 )

Since 2020, over ten million scholarly articles have been published annually. To put that into perspective, say all ten million articles were released on the first day of the year.

Uncovering The Secrets Behind The Most Influential Scholarly Publications With AceMap

Understanding the Balance between Internal Knowledge and External Sources

Author Qingqin Fang (

 ORCID:

0009–0003–5348–4264) Introduction Previous research often emphasized the limitations of LLM’s information acquisition pathways, focusing on enhancing its capabilities in this regard.

When RAG and LLM Conflict: Who Will AI Listen to?

Solutions to Enhance LLM Performance in Long Contexts Author · Qingqin Fang (

 ORCID:

0009–0003–5348–4264) Introduction In the era of AI breakthroughs, large language models (LLMs) are not just advancements; they are revolutions, transforming how we interact with technology, from casual conversations with chatbots to the intricate mechanisms behind sophisticated data analysis tools.

Navigating the Long Context Conundrum: Challenges in Language Models’ Information Processing

Supervised Fine-tuning, Reinforcement Learning from Human Feedback and the latest SteerLM Author · Xuzeng He (

 ORCID:

0009–0005–7317–7426) Introduction Large Language Models (LLMs), usually trained with extensive text data, can demonstrate remarkable capabilities in handling various tasks with state-of-the-art performance. However, people nowadays typically want something more personalised instead of a general solution.

Fine-tuning Large Language Models: A Brief Introduction

An Overview of Constructing a Knowledge Graph Author · Qingqin Fang (

 ORCID:

0009–0003–5348–4264) 1. Introduction 1.1 What is a Knowledge Graph Knowledge Graphs are structured semantic knowledge bases used to rapidly describe concepts and their relationships in the physical world.

Unlocking Intelligence: The Journey from Data to Knowledge Graph

Author Dhruv Gupta (

 ORCID

: 0009–0004–7109–5403) Introduction Large Language Models (LLMs) have become the new face of Natural language processing (NLP). With their generative power and ability to comprehend human language, the human reliance on these models is increasing every day. However, the LLMs have been known to hallucinate and thus produce wrong outputs.

Prompt engineering: A Way to Smartly Use AI

Latest effort in assessing the security of the code generated by large language models Author · Xuzeng He (

 ORCID:

0009–0005–7317–7426) Introduction With the surge of Large Language Models (LLMs) nowadays, there is a rising trend among developers to use Large Language Models to assist their daily code writing. Famous products include GitHub Copilot or simply ChatGPT.

Large Language Models for Code Writing: Security Assessment

Research Graph

Google’s Groundbreaking AI Model Explained
 


 Introduction

In the rapidly evolving landscape of artificial intelligence, Google continues to stand at the forefront, consistently pushing the boundaries of what these technologies can achieve. One of their latest advancements, GEMMA2, represents a significant leap in AI capabilities.

What is Gemma2?

Stories by Research Graph on Medium

#### Integrating temporal data into static knowledge graphs

<figure>
<img
src="https://cdn-images-1.medium.com/max/1000/0*rzpFvqVUm54hT6S6" />
<figcaption>Photo by Djim Loic on <a
href="https://unsplash.com/photos/analog-clock-at-12-am-ft0-Xu4nTvA?utm_content=creditShareLink&amp;utm_medium=referral&amp;utm_source=unsplash">Unsplash</a></figcaption>
</figure>

### **Author**

- Amanda Kau **(ORCID:**
 [**0009--0004--4949--9284**](https://orcid.org/0009-0004-4949-9284)**)**

### Introduction

Knowledge graphs (KGs) have proven to be an effective method of data
representation that is increasingly popular. In KGs, entities and
concepts are represented as nodes, while the relationships between nodes
are depicted as edges. Thus, KGs can effectively capture the semantic
meanings of nodes. For instance, Google's Knowledge Graph distinguishes
between different meanings of a word by identifying its context via its
neighbours.

Recently, there has been more discourse suggesting that traditional,
static KGs are insufficient as they only capture knowledge up to the
current point in time. KGs used for online search must update as new
entities and knowledge emerge or words adopt new meanings. In social
media platforms, KGs that capture user data and relationships have to
update dynamically as new users are created and follow other accounts.
In this article, we will introduce knowledge graphs that incorporate
temporal information, namely dynamic knowledge graphs (DKGs) and
temporal knowledge graphs (TKGs). We briefly describe DKG construction
techniques and the two definitions of TKGs. Then, we will review a
series of DKG and TKG applications in existing literature.

### The Distinction Between Dynamic and Temporal Knowledge Graphs

Before diving in, there is an important distinction that should be
noted. During research, the terms "dynamic knowledge graph" and
"temporal knowledge graph" kept turning up, but the distinction between
them was blurry, at least for me. This is what I discovered upon further
research.

**DKGs** primarily focus on understanding structural changes in graphs
over time. They rely on evolving datasets to add or update nodes and
edges. This learning of meta-knowledge seeks to shed light on the
evolution of the graph's structural and semantic properties, rather than
specific content within individual nodes and edges.

On the other hand, **TKGs** are a special subset of DKGs. They have an
added capability of storing event timestamps, ensuring data consistency
with regards to time. Research involving TKGs focuses on studying
individual nodes and edges, which is useful for link prediction and time
prediction that aim to anticipate events between entities and the time
of their occurrences.

It is important to note that DKGs and TKGs are by no means mutually
exclusive. Some studies may focus solely on updating dynamic graphs or
studying graph structures, whilst others focus on link and time
predictions. There are also works that encompass a mix of these tasks.
Research goals depend heavily on domain and applications. Nonetheless,
there is a common thread across approaches of maintaining the validity
of data over time.

### Dynamic Knowledge Graphs

#### **Motivation for DKGs**

<figure>
<img
src="https://cdn-images-1.medium.com/max/1000/0*IUOSmcEaWhiqaLSD" />
<figcaption>Dynamic knowledge graphs allow for updates to the graph’s
nodes and edges at different time steps. Source: <a
href="https://blog.x.com/engineering/en_us/topics/insights/2021/temporal-graph-networks">https://blog.x.com/engineering/en_us/topics/insights/2021/temporal-graph-networks</a></figcaption>
</figure>

The world, along with our knowledge of it, is dynamic. Therefore, our
representations of the world should also reflect this dynamism and
evolve over time. Much of the data we generate already includes
timestamps, laying the groundwork for a seamless transition from KGs to
DKGs. Consider, for example, a social media network like X (formerly
known as Twitter), where users can be represented as nodes with
relationships like "User A follows User B." With reference to the image
above, DKGs can be updated with every new event, such as the creation of
a new account (new node), a user following another user (new edge), or a
user updating their profile (node update). These updates allow for a
more complete and accurate representation of our evolving world
knowledge.

#### **DKG Construction**

<figure>
<img
src="https://cdn-images-1.medium.com/max/1000/0*3e8-kzgqacCFvv00" />
<figcaption>A pipeline showing the process of DKG construction. Source:
Farghaly et al., 2024 <a
href="https://doi.org/10.1109/access.2024.3378514">https://doi.org/10.1109/access.2024.3378514</a></figcaption>
</figure>

The construction of DKGs is not vastly different from that of standard
KGs. Standard KGs are formed in the KG construction phase, which
involves entity and relationship extraction that can be further broken
down into various natural language processing subtasks. For DKGs, an
additional KG completion phase is employed. This phase is responsible
for dynamically updating or adding new nodes and relations to an
existing KG and can be achieved in two ways:

1. **Inference-based completion**: New knowledge is derived from
 studying the existing graph and added into the KG.
2. **Extraction-based completion**: A new KG is constructed with
 external data sources, then linked to the existing KG, thereby
 fusing the knowledge sources.

Both of these approaches ensure that the knowledge in DKGs remains
up-to-date.

### Temporal Knowledge Graphs

#### **Motivation for TKGs**

In the previous section, we mentioned that TKGs incorporate timestamps
of events. The lack of temporal data can make the representation
confusing. Consider panel (a) in the image below, where three
relations--*Praise or endorse, Make optimistic comment* and *Criticise
or denounce*--are shown between *Barack Obama* and *Iran*. Together,
these actions seem contradictory and incoherent.

<figure>
<img
src="https://cdn-images-1.medium.com/max/1000/0*fBwDThwQH6G8U4aW" />
<figcaption>Standard knowledge graphs in panel (a) may be confusing,
thus requiring the integration of temporal data as shown in panel (b).
Source: Zhang et al., 2023 <a
href="https://doi.org/10.1007/978-3-031-46664-9_4">https://doi.org/10.1007/978-3-031-46664-9_4</a></figcaption>
</figure>

When we introduce temporal data, for instance in the image above in
panel (b), we see that Obama's actions toward Iran occurred in three
distinct years from 2013 to 2015 and were tied to actions by other
countries. This added context makes the information a lot more
understandable.

#### **How is temporal data added into KGs?**

Traditional KG data is commonly expressed as a triple comprising a
subject, predicate, and object. The subject and object form two separate
nodes, while the predicate is a relation connecting them. In the earlier
example, *Barack Obama* and *Iran* would be two nodes connected by a
relation *Praise or endorse*.

There are two distinct definitions of TKGs:

1. **Temporal Knowledge Graphs (TKGs)**

Instead of a triple, TKG data is typically represented as quadruples
consisting of the subject, predicate, object, and timestamp. In the same
example as before, this would be *(Barack Obama, Make optimistic
comment, Iran, 2014--12--29)*. Some implementations might extend this
further to quintuples where there is a time range, such as *(Donald
Trump, President of, United States, 2017, 2021)*.

1. **Discrete Time Dynamic Graphs (DTDGs)**

DTDGs, unlike TKGs, are a series of static KGs that use the standard
triple representation. This definition allows for easier temporal
analysis and meta-knowledge mining, which focuses on the graph's
structural and semantic properties rather than the individual nodes and
edges themselves.

### Applications

#### **Dynamic Knowledge Graphs**

The powerful ability of DKGs to capture semantics and relationships
dynamically offer advantages in numerous domains, including
question-answering, linguistics, finance, fake review detection in
e-commerce, robotics, smart cities and Internet of Things, animations,
and more. Another field of research termed [Temporal Graph
Learning](https://towardsdatascience.com/temporal-graph-learning-in-2023-d28d1640dbf2#f7ab)
also attempts to learn from evolving TKGs and has applications in
disease modelling, anomaly detection and detecting misinformation. We
will discuss some applications below.

1. **Detecting emerging communities of knowledge**

Aparicio et al. (2024) constructed DTDGs from publications in the
Conference on Knowledge Discovery and Data Mining (KDD) to analyse
research trends within the conference over the years. A series of
knowledge graphs were created for every year from 2013 to 2021.
Comparing graph structures across the years allowed them to identify
trends such as increased focus on topics like "graph" and "e-commerce"
and emerging publications emphasising interconnected topics rather than
single topics. These valuable insights into research trends which allows
researchers to anticipate future research directions and allows
organisations to get a glimpse of possible industry developments.

**2. Linguistics --- Updating graphs with neologisms**

Neologisms involve the coining of new words or assignment of new
meanings to existing words, and reflect the evolution of language across
generations. Since KGs aim to capture the knowledge we have about the
world, they should be dynamically updated to reflect these new words and
meanings. This was the goal of the auto-growing KG, PolarisX (Polaris
Expander), which crawled news sites and social media, extracted
information using the BERT large language model, and added new knowledge
to KGs. Conversational chatbots, sentiment analysis systems, search
engines, and other applications can benefit from these KGs through more
effective understanding of user intent and semantics.

#### **Temporal Knowledge Graphs**

Tasks achieved using TKGs are entity prediction, relation prediction,
and time prediction. If TKG data is represented as quadruples *(s, r, o,
t)*, then entity prediction can be modelled by queries like *(?, r, o,
t)* or *(s, r, ?, t)*, while relation and time prediction can be
modelled as *(s, ?, o, t)* and *(s, r, o, ?)*. These TKG reasoning tasks
can be categorised into two settings given that we have data within a
certain time range:

1. **Interpolation** focuses on predicting missing facts within the
 time range by learning embeddings for entities and relations.

One interpolation task is TKG completion, aimed at inferring missing
entities or relations within TKGs to fill in missing facts. Existing
literature for TKG completion is often more mathematical as relations
are modelled by rotations and translations in space. Initially,
entities, relations, and times were encoded in real space. Later, this
was extended to complex space, and then to hypercomplex space. Cai et
al. (2024) used quaternions to represent information in hypercomplex
space, which have one real part and three imaginary parts as compared to
standard complex numbers that have one real part and one imaginary part,
thus allowing more information to be expressed.

**2. Extrapolation** predicts facts beyond the time range by reasoning
over a series of graph snapshots at each timestamp.

Extrapolation is slightly more interesting as it is akin to predicting
the future. To predict whether and when an event might occur, Trivedi et
al. (2017) presented Know-Evolve. It employed a recurrent neural network
to learn the historical evolution of entities while using a bilinear
relationship score to understand temporal dependencies between entities.

### TKG Forecasting with Large Language Models

Recently, Lee et al. (2023) used in-context learning (ICL) with large
language models (LLMs) to perform the future link prediction task. The
authors highlighted that prior forecasting techniques using TKGs
required special model architectures, large training datasets with
comprehensive historical information, and posed challenges in model
selection. In response, they performed ICL on LLMs, a process which
entails providing a few examples to the LLM so it can learn to perform
on unseen tasks.

Their approach utilised a three-stage pipeline. Initially, relevant
facts were retrieved from a TKG to serve as context. This context was
transformed into a prompt and fed to the LLM. The LLM's output was then
converted into probabilities, where the most probable entity was
selected as the forecasted answer. In this way, their method could
predict events without time-consuming training or custom model
architectures. Remarkably, it was shown that LLMs performed as well as
current TKG techniques, even without explicit modules designed to
capture associations within the data. Moreover, the model could learn
patterns from historical data and the LLM was not simply predicting
based on the most common or recent facts given in the context. This
unveils the potentials of LLMs to be studied with TKGs.

### Conclusion

In conclusion, we started off by clarifying the distinction between
temporal knowledge graphs (TKGs) and dynamic knowledge graphs (DKGs),
both of which are forms of knowledge graphs that accommodate temporal
changes to data. We discussed the motivation for exploring DKGs and
TKGs, together with a brief description of DKG construction techniques.
We introduced two distinct definitions of TKGs, Temporal Knowledge
Graphs and Discrete Time Dynamic Graphs.

A review of existing DKG and TKG applications was conducted. In
particular, DKGs can be utilised in a number of industries and
applications, including detecting communities of knowledge and aiding in
linguistics. TKG applications focus on entity, relation or time
prediction tasks, which are broadly categorised into interpolation or
extrapolation methods. Examples include TKG completion and future event
prediction respectively.

Finally, we reviewed a recent study where large language models (LLMs)
were employed for TKG prediction. This introduces questions about the
necessity of specially designed and sophisticated TKG models and the
potential for LLMs to revolutionise this field. However, given the
current limitations of LLMs, it is conceivable that the relationship
between TKGs and LLMs may evolve similarly to that between traditional
KGs and LLMs from a competitive to a complementary relationship.

### **References**

- Wang, A. (2020, November 20). Difference Between Temporal KG and
 Dynamic KG. Medium.
 <https://audreywongkg.medium.com/difference-between-temporal-kg-and-dynamic-kg-7b25a8075df3#:~:text=Temporal%20knowledge%20graph%20embedding%20methods%20are%20trained%20on%20stationary%20datasets>
- Farghaly, M., Mounir, M., Aref, M., & Moussa, S. M. (2024).
 Investigating the Challenges and Prospects of Construction Models for
 Dynamic Knowledge Graphs. In IEEE Access (Vol. 12, pp. 40973--40988).
 Institute of Electrical and Electronics Engineers (IEEE).
 <https://doi.org/10.1109/access.2024.3378514>
- Aparicio, J. T., Arsenio, E., Santos, F., & Henriques, R. (2024).
 Using dynamic knowledge graphs to detect emerging communities of
 knowledge. In Knowledge-Based Systems (Vol. 294, p. 111671). Elsevier
 BV. <https://doi.org/10.1016/j.knosys.2024.111671>
- Yoo, S., & Jeong, O. (2020). Automating the expansion of a knowledge
 graph. In Expert Systems with Applications (Vol. 141, p. 112965).
 Elsevier BV. <https://doi.org/10.1016/j.eswa.2019.112965>
- Cai, L., Mao, X., Wang, Z., Zhao, S., Zhou, Y., Wu, C., & Lan, M.
 (2024). Temporal Knowledge Graph Completion with Time-sensitive
 Relations in Hypercomplex Space (Version 1). arXiv.
 <https://doi.org/10.48550/ARXIV.2403.02355>
- Trivedi, R., Dai, H., Wang, Y., & Song, L. (2017). Know-Evolve: Deep
 Temporal Reasoning for Dynamic Knowledge Graphs (Version 3). arXiv.
 <https://doi.org/10.48550/ARXIV.1705.05742>
- Lee, D.-H., Ahrabian, K., Jin, W., Morstatter, F., & Pujara, J.
 (2023). Temporal Knowledge Graph Forecasting Without Knowledge Using
 In-Context Learning (Version 3). arXiv.
 <https://doi.org/10.48550/ARXIV.2305.10613>

![](https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=c35a205a520a){width="1"
height="1"}