GraphNews

Now apart from #SPARQL (https://lnkd.in/ey_6S_6B) there is also a #SHACL wiki https://lnkd.in/ek9PHN9z It is a first release with much to fix, improve and…

One of my co-workers asked the other day if we could use an LLM to track the relationships between characters in his favorite book series…

Large language models (LLMs), such as ChatGPT and GPT4, are making new waves in the field of natural language processing and artificial intelligence, due to their emergent ability and generalizability. However, LLMs are black-box models, which often fall short of capturing and accessing factual knowledge. In contrast, Knowledge Graphs (KGs), Wikipedia and Huapu for example, are structured knowledge models that explicitly store rich factual knowledge. KGs can enhance LLMs by providing external knowledge for inference and interpretability. Meanwhile, KGs are difficult to construct and evolving by nature, which challenges the existing methods in KGs to generate new facts and represent unseen knowledge. Therefore, it is complementary to unify LLMs and KGs together and simultaneously leverage their advantages. In this article, we present a forward-looking roadmap for the unification of LLMs and KGs. Our roadmap consists of three general frameworks, namely, 1) KG-enhanced LLMs, which incorporate KGs during the pre-training and inference phases of LLMs, or for the purpose of enhancing understanding of the knowledge learned by LLMs; 2) LLM-augmented KGs, that leverage LLMs for different KG tasks such as embedding, completion, construction, graph-to-text generation, and question answering; and 3) Synergized LLMs + KGs, in which LLMs and KGs play equal roles and work in a mutually beneficial way to enhance both LLMs and KGs for bidirectional reasoning driven by both data and knowledge. We review and summarize existing efforts within these three frameworks in our roadmap and pinpoint their future research directions.

👏 #research Excellent paper: Unifying Large Language Models and Knowledge Graphs: A Roadmap ⁉ What is it important work in the right direction? ☠ Despite…

The way we engage with Large Language Models (LLMs) is rapidly evolving. We started with prompt engineering and progressed to combining prompts into 'Chains of…

Discover the fascinating fusion of knowledge graphs and LLMs in Neuro-symbolic AI, unlocking new frontiers of understanding and intelligence.

Graph neural architecture search has sparked much attention as Graph Neural Networks (GNNs) have shown powerful reasoning capability in many relational tasks. However, the currently used graph search space overemphasizes learning node features and neglects mining hierarchical relational information. Moreover, due to diverse mechanisms in the message passing, the graph search space is much larger than that of CNNs. This hinders the straightforward application of classical search strategies for exploring complicated graph search space. We propose Automatic Relation-aware Graph Network Proliferation (ARGNP) for efficiently searching GNNs with a relation-guided message passing mechanism. Specifically, we first devise a novel dual relation-aware graph search space that comprises both node and relation learning operations. These operations can extract hierarchical node/relational information and provide anisotropic guidance for message passing on a graph. Second, analogous to cell proliferation, we design a network proliferation search paradigm to progressively determine the GNN architectures by iteratively performing network division and differentiation. The experiments on six datasets for four graph learning tasks demonstrate that GNNs produced by our method are superior to the current state-of-the-art hand-crafted and search-based GNNs. Codes are available at https://github.com/phython96/ARGNP.

Pretrained Language Models (PLMs) such as BERT have revolutionized the landscape of Natural Language Processing (NLP). Inspired by their proliferation, tremendous efforts have been devoted to Pretrained Graph Models (PGMs). Owing to the powerful model architectures of PGMs, abundant knowledge from massive labeled and unlabeled graph data can be captured. The knowledge implicitly encoded in model parameters can benefit various downstream tasks and help to alleviate several fundamental issues of learning on graphs. In this paper, we provide the first comprehensive survey for PGMs. We firstly present the limitations of graph representation learning and thus introduce the motivation for graph pre-training. Then, we systematically categorize existing PGMs based on a taxonomy from four different perspectives. Next, we present the applications of PGMs in social recommendation and drug discovery. Finally, we outline several promising research directions that can serve as a guideline for future research.

The telecom virtualization and automation pioneer partners with vector-native database provider KX to enable next generation AI-powered telecom operations

Graph Neural Networks (GNNs) have shown exceptional performance in the task of link prediction. Despite their effectiveness, the high latency brought by non-trivial neighborhood data dependency limits GNNs in practical deployments. Conversely, the known efficient MLPs are much less effective than GNNs due to the lack of relational knowledge. In this work, to combine the advantages of GNNs and MLPs, we start with exploring direct knowledge distillation (KD) methods for link prediction, i.e., predicted logit-based matching and node representation-based matching. Upon observing direct KD analogs do not perform well for link prediction, we propose a relational KD framework, Linkless Link Prediction (LLP), to distill knowledge for link prediction with MLPs. Unlike simple KD methods that match independent link logits or node representations, LLP distills relational knowledge that is centered around each (anchor) node to the student MLP. Specifically, we propose rank-based matching and distribution-based matching strategies that complement each other. Extensive experiments demonstrate that LLP boosts the link prediction performance of MLPs with significant margins, and even outperforms the teacher GNNs on 7 out of 8 benchmarks. LLP also achieves a 70.68x speedup in link prediction inference compared to GNNs on the large-scale OGB dataset.

What are the limitations of LLMs, and how to overcome them

🔥✌️The future of knowledge graphs in times of Large Language Model (LLMs).👇 How knowledge will be stored and structured, e.g. by Google, in the future is a… | 15 comments on LinkedIn

The concept of a knowledge graph has, since its (re-)introduction in 2012, come to assume a pivotal role in the development of a range of crucial…

Graph neural networks (GNNs) have various practical applications, such as drug discovery, recommendation engines, and chip design. However, GNNs lack transparency as they cannot provide understandable explanations for their predictions. To address this issue, counterfactual reasoning is used. The main goal is to make minimal changes to the input graph of a GNN in order to alter its prediction. While several algorithms have been proposed for counterfactual explanations of GNNs, most of them have two main drawbacks. Firstly, they only consider edge deletions as perturbations. Secondly, the counterfactual explanation models are transductive, meaning they do not generalize to unseen data. In this study, we introduce an inductive algorithm called INDUCE, which overcomes these limitations. By conducting extensive experiments on several datasets, we demonstrate that incorporating edge additions leads to better counterfactual results compared to the existing methods. Moreover, the inductive modeling approach allows INDUCE to directly predict counterfactual perturbations without requiring instance-specific training. This results in significant computational speed improvements compared to baseline methods and enables scalable counterfactual analysis for GNNs.

Healthcare knowledge graphs (HKGs) have emerged as a promising tool for organizing medical knowledge in a structured and interpretable way, which provides a comprehensive view of medical concepts and their relationships. However, challenges such as data heterogeneity and limited coverage remain, emphasizing the need for further research in the field of HKGs. This survey paper serves as the first comprehensive overview of HKGs. We summarize the pipeline and key techniques for HKG construction (i.e., from scratch and through integration), as well as the common utilization approaches (i.e., model-free and model-based). To provide researchers with valuable resources, we organize existing HKGs (The resource is available at https://github.com/lujiaying/Awesome-HealthCare-KnowledgeBase) based on the data types they capture and application domains, supplemented with pertinent statistical information. In the application section, we delve into the transformative impact of HKGs across various healthcare domains, spanning from fine-grained basic science research to high-level clinical decision support. Lastly, we shed light on the opportunities for creating comprehensive and accurate HKGs in the era of large language models, presenting the potential to revolutionize healthcare delivery and enhance the interpretability and reliability of clinical prediction.

How a wise use of direction when doing message passing on heterophilic graphs can result in very significant gains.

I’ve been comparing ChatGPT responses using statistical similarity v knowledge representations in the automated text selection process. There are token…

Sharing SPARQL queries in Wikibase! Check it out: https://t.co/3FsC4xVRGlWikibase simplifies working with knowledge graphs by allowing users to share predefined SPARQL queries. It seamlessly integrates into the query service, making data exploration easier.#graphdatabase #data pic.twitter.com/bFVaZSh60t— The QA Company (@TheQACompany) May 31, 2023

The scientific work of members of our Department was published in the monograph "Information Technology for Management: Approaches to Improving Business and Society" published by the Springer. The research concerns the automatic assessment of the quality of Wikipedia articles and the reliability of

By Paula Wojcik, Bastian Bunzeck & 1 more. This articles explores character representations in Wikidata across various language editions.

The OntoGPT framework and SPIRES tool provide a principled approach to extract knowledge from unstructured text for integration into Knowledge Graphs (KGs), using Large Language Models such as GPT. This methodology enables handling complex relationships, ensures logical consistency, and aligns with predefined ontologies for better KG integration.

A Content Graph case study on how the Data Graphs website is self powered - entirely knowledge graph driven

Nature Machine Intelligence - Designing methods to induce explicit and deep structural constraints in latent space at the sample level is an open problem in natural language processing-derived...

Graph Neural Networks can be used for a variety of applications but do you know what it takes to create a great recommendation system? Dive deep into the math of GNNs, implement a link prediction module and show everyone how stunning graph machine learning can be!

Change & Risk Require New Enterprise Tools As AI systems, bots (both digital and physical), AI leveraged smart digital identities, and IoT devices invade your enterprise, it increases the pace of change and risk. This brief article focuses on why you should be deploying TODA, EMS and graphs in your

SAN FRANCISCO, May 30, 2023 -- ArangoDB, the company behind the most complete graph data and analytics platform, today announced the GA release of

Ontotext receives growth funding to strengthen its leadership in the knowledge graph market and develop end-to-end vertical offerings.