GraphNews

Transport for London implements advanced digital technologies to manage congestion and improve efficiency on London's roads.

A word of caution from Netflix against blindly using cosine similarity as a measure of semantic similarity: https://lnkd.in/gX3tR4YK They study linear matrix… | 12 comments on LinkedIn

Graph neural networks (GNNs) have revolutionized machine learning for graph-structured data. Unlike traditional neural networks, GNNs are good at capturing intricate relationships in graphs…

Nature Reviews Methods Primers - Graph neural networks are a class of deep learning methods that can model physical systems, generate new molecules and identify drug candidates. This Primer...

Graph-structured data exhibits universality and widespread applicability across diverse domains, such as social network analysis, biochemistry, financial fraud detection, and network security. Significant strides have been made in leveraging Graph Neural Networks (GNNs) to achieve remarkable success in these areas. However, in real-world scenarios, the training environment for models is often far from ideal, leading to substantial performance degradation of GNN models due to various unfavorable factors, including imbalance in data distribution, the presence of noise in erroneous data, privacy protection of sensitive information, and generalization capability for out-of-distribution (OOD) scenarios. To tackle these issues, substantial efforts have been devoted to improving the performance of GNN models in practical real-world scenarios, as well as enhancing their reliability and robustness. In this paper, we present a comprehensive survey that systematically reviews existing GNN models, focusing on solutions to the four mentioned real-world challenges including imbalance, noise, privacy, and OOD in practical scenarios that many existing reviews have not considered. Specifically, we first highlight the four key challenges faced by existing GNNs, paving the way for our exploration of real-world GNN models. Subsequently, we provide detailed discussions on these four aspects, dissecting how these solutions contribute to enhancing the reliability and robustness of GNN models. Last but not least, we outline promising directions and offer future perspectives in the field.

Introducing PyGraft: A Powerful Tool for Generating Synthetic Knowledge Graphs ... A new open-source tool called PyGraft is now available that enables the… | 13 comments on LinkedIn

Here are the slides I used for my 09-FEB-2024 keynote presentation "Knowledge Graphs: An Industry Perspective" at Dagstuhl Seminar 24061: "Are Knowledge Graphs…

I am thrilled to introduce a new AI Study Guide (https://lnkd.in/g4rPZVHW) dedicated to Tony Seale, another of my favorite authors, thought leaders, and…

Email : jeongiitae6@gmail.com

Knowledge graphs (KGs) have emerged as a prominent data representation and management paradigm. Being usually underpinned by a schema (e.g., an ontology), KGs capture not only factual information but also contextual knowledge. In some tasks, a few KGs established themselves as standard benchmarks. However, recent works outline that relying on a limited collection of datasets is not sufficient to assess the generalization capability of an approach. In some data-sensitive fields such as education or medicine, access to public datasets is even more limited. To remedy the aforementioned issues, we release PyGraft, a Python-based tool that generates highly customized, domain-agnostic schemas and KGs. The synthesized schemas encompass various RDFS and OWL constructs, while the synthesized KGs emulate the characteristics and scale of real-world KGs. Logical consistency of the generated resources is ultimately ensured by running a description logic (DL) reasoner. By providing a way of generating both a schema and KG in a single pipeline, PyGraft's aim is to empower the generation of a more diverse array of KGs for benchmarking novel approaches in areas such as graph-based machine learning (ML), or more generally KG processing. In graph-based ML in particular, this should foster a more holistic evaluation of model performance and generalization capability, thereby going beyond the limited collection of available benchmarks. PyGraft is available at: https://github.com/nicolas-hbt/pygraft.

Using vector databases in retrieval-augmented generation (RAG) raises concerns about relevance, since the info retrieved may not be semantically related to the…

KGLM-Loop: A Bi-Directional Data Flywheel for Knowledge Graph Refinement and Hallucination Detection in Large Language Models ☀ 🌑 In the pursuit of…

We've been hearing the term "Semantic layer" without truly understanding the semantics of it. So, here is episode 11 of #DnABytes and today's topic is:…

Situation I stumbled upon an interesting LinkedIn post, courtesy of Kurt Cagle, about the term ‘Data Product,’ authored by Juha Korpela. Naturally, I appreciate the essence of the post, which emphasizes the importance of defining terminology in a platform-agnostic manner.

Telecom GenAI based Network Operations: The Integration of LLMs, GraphRAG, Reinforcement Learning, and Scoring Models With the increasing complexity of… | 12 comments on LinkedIn

LLM frameworks like LangChain are moving towards a graph-based approach for handling their workflows. This represents the initial steps of a much larger… | 90 comments on LinkedIn

🚀 Join us for a special webinar on March 6th, 8am PT/5pm CET, as we unveil the latest in GNN technology - PyG 2.5! 🎉 Dive deep into the features with a live…

Deep graph models (e.g., graph neural networks and graph transformers) have become important techniques for leveraging knowledge across various types of graphs. Yet, the scaling properties of deep graph models have not been systematically investigated, casting doubt on the feasibility of achieving large graph models through enlarging the model and dataset sizes. In this work, we delve into neural scaling laws on graphs from both model and data perspectives. We first verify the validity of such laws on graphs, establishing formulations to describe the scaling behaviors. For model scaling, we investigate the phenomenon of scaling law collapse and identify overfitting as the potential reason. Moreover, we reveal that the model depth of deep graph models can impact the model scaling behaviors, which differ from observations in other domains such as CV and NLP. For data scaling, we suggest that the number of graphs can not effectively metric the graph data volume in scaling law since the sizes of different graphs are highly irregular. Instead, we reform the data scaling law with the number of edges as the metric to address the irregular graph sizes. We further demonstrate the reformed law offers a unified view of the data scaling behaviors for various fundamental graph tasks including node classification, link prediction, and graph classification. This work provides valuable insights into neural scaling laws on graphs, which can serve as an essential step toward large graph models.

Data provenance is something people love in theory, but never practice... I have just rewatched an excellent appearance by Jaron Lanier from a couple of… | 52 comments on LinkedIn

6 Rules to help you decide whether to use a graph or a table to solve your analytics problem.

Machine learning on graphs, especially using graph neural networks (GNNs), has seen a surge in interest due to the wide availability of graph data across a broad spectrum of disciplines, from life to social and engineering sciences. Despite their practical success, our theoretical understanding of the properties of GNNs remains highly incomplete. Recent theoretical advancements primarily focus on elucidating the coarse-grained expressive power of GNNs, predominantly employing combinatorial techniques. However, these studies do not perfectly align with practice, particularly in understanding the generalization behavior of GNNs when trained with stochastic first-order optimization techniques. In this position paper, we argue that the graph machine learning community needs to shift its attention to developing a more balanced theory of graph machine learning, focusing on a more thorough understanding of the interplay of expressive power, generalization, and optimization.

Complex networks pervade various real-world systems, from the natural environment to human societies. The essence of these networks is in their ability to transition and evolve from microscopic disorder-where network topology and node dynamics intertwine-to a macroscopic order characterized by certain collective behaviors. Over the past two decades, complex network science has significantly enhanced our understanding of the statistical mechanics, structures, and dynamics underlying real-world networks. Despite these advancements, there remain considerable challenges in exploring more realistic systems and enhancing practical applications. The emergence of artificial intelligence (AI) technologies, coupled with the abundance of diverse real-world network data, has heralded a new era in complex network science research. This survey aims to systematically address the potential advantages of AI in overcoming the lingering challenges of complex network research. It endeavors to summarize the pivotal research problems and provide an exhaustive review of the corresponding methodologies and applications. Through this comprehensive survey-the first of its kind on AI for complex networks-we expect to provide valuable insights that will drive further research and advancement in this interdisciplinary field.

Writer CEO May Habib says its semantic graphing approach is an alternative to the chunking process of RAG using vector databases.

Data provenance is something people love in theory, but never practice... I have just rewatched an excellent appearance by Jaron Lanier from a couple of… | 39 comments on LinkedIn

Relational Harmony and a New Hope for Dimensionality ⛓️ In an era where data complexity escalates and the quest for meaningful technology integration… | 30 comments on LinkedIn

Knowledge hypergraphs are garnering a lot of attention – and deservedly so. You can find my two previous posts on knowledge hypergraphs and on more adaptive conceptualizations for hypergraphs as well as Kurt Cagle's focused and more practically minded pieces on Hypergraphs and RDF, on Named Graphs (