GraphNews

Data semantics is harder than rocket science! Hear Juan Sequeda argue why enterprises need to be investing in semantics. https://lnkd.in/gKV-Prk4 High…

Unlocking universal reasoning across knowledge graphs. Knowledge graphs (KGs) are powerful tools for organizing and reasoning over vast amounts of… | 13 comments on LinkedIn

“Chat with a PDF” is so 2023. In 2024 we turn 1,000 PDFs into knowledge. In 2023, GenAI exploded and everyone had a side project to "chat with a PDF." That… | 22 comments on LinkedIn

Graph RAG answers the big questions where text embeddings won’t help you.

🚀 Exciting New Research: "Graph-constrained Reasoning (GCR)" - Enabling Faithful KG-grounded LLM Reasoning with Zero Hallucination! 🧠 🎉 Proud to share our… | 11 comments on LinkedIn

GraphRAG explained with an imaginary quiz game and not a single line of source code

Applications of Graph approaches in RAG — current state

A GCP native, fully serverless implementation that you will replicate in minutes

In this video, I introduce LightRAG, a new, cost-effective retrieval augmented generation (RAG) method that combines knowledge graphs and embedding-based ret...

⛔ The current challenge in building KGs from unstructured documents using LLMs is ensuring that the extracted triplets fully capture the provided context. 🟢…

Data Structures for Hyper-Personalized Lesson Plans

Document Metadata Generation, File Directory & Two-Step Information Retrieval Processes

Learn how to turn CSV files into graph models using LLMs, simplifying data relationships, enhancing insights, and optimizing workflows.

“Ever wondered how to find or build Knowledge Graphs that power everything from recommendation engines to drug discovery?”

The 3 layers of Agentic Graph RAG 💬 The 3 layers of agentic graph RAG represent a significant advancement in AI-driven knowledge systems. These layers… | 17 comments on LinkedIn

Researchers created a knowledge graph based on 58 million journal papers to fuel personalized research ideas for scientists. Over 4400 ideas generated by the… | 29 comments on LinkedIn

Hello wonderful people, I’ve noticed some common misconceptions about graphs and AI circulating on LinkedIn, and I thought it might be helpful to share some insights to clarify these topics. I hope…

Glean | Glean’s knowledge graph and signals enables it to provide state-of-the-art hybrid search and generative AI that only gets better over time.

🧠 Knowledge-driven data access means accessing data through an ontology used to represent its meaning at a conceptual level. 🔎 Connecting an enterprise…

A curated list of resources for graph-related topics, including graph databases, analytics and science - graphgeeks-lab/awesome-graph-universe

A recent post I wrote on LinkedIn hit a nerve. Talking about information/semantic rich projects failing due to the lack of organizational commitment is not new, for me or others in the field.

As a technology SME in the KM space, I am excited about the changes happening in the semantic software industry. Just two years ago, in my book, I provided a complete analysis of the leading providers of taxonomy and ontology management systems, as well as graph providers, auto-tagging systems, and more. While the software products I evaluated are still around, most of them have new owners.

RDF vs LPG: Friends or Foes? For over a decade, ever since #KnowledgeGraphs (KGs) gained prominence, there has been intense competition between #RDF (also…

After a period of more than a year (can't believe time flew by so quick!), I had the pleasure of going back for a second time on the Practical AI Podcast with…

500 million+ members | Manage your professional identity. Build and engage with your professional network. Access knowledge, insights and opportunities.

Cosdata: A cutting-edge AI data platform for next-gen search pipelines. Features semantic search, knowledge graphs, hybrid capabilities, real-time scalability, and ML integration. Designed for immu...

Recently, knowledge-graph-enhanced recommendation systems have attracted much attention, since knowledge graph (KG) can help improving the dataset quality and offering rich semantics for explainable recommendation. However, current KG-enhanced solutions focus on analyzing user behaviors on the product level and lack effective approaches to extract user preference towards product category, which is essential for better recommendation because users shopping online normally have strong preference towards distinctive product categories, not merely on products, according to various user studies. Moreover, the existing pure embedding-based recommendation methods can only utilize KGs with a limited size, which is not adaptable to many real-world applications. In this paper, we generalize the recommendation problem with preference mining as a compound knowledge reasoning task and propose a novel multi-agent system, called Mcore, which can promote model performance by mining users’ high-level interests and is adaptable to large KGs. Specifically, we split the overall problem and allocate sub-task to each agent: Coordinate Agent takes charge of recognizing the product-category preference of current user, while Relation Agent and Entity Agent perform KG reasoning cooperatively from a user node towards the preferred categories and terminate at a product node as recommendation. To train this heterogeneous multi-agent system, where agents own various functionalities, we propose an asynchronous reinforcement training pipeline, called Multi-agent Collaborative Learning. The extensive experiments on real datasets demonstrate the effectiveness and adaptability of Mcore on recommendation tasks.

Author Dan Selman shows how easy it is to implement convert natural language text to nodes and edges in a knowledge graph using a new class and method in his demonstration project.