DeepGraphLibrary

Coming to #KDD2024? Mark your day by attending our tutorial "Graph Machine Learning Meets Multi-table Relational Data" on the first afternoon of the conference! @kdd_news @AmazonScience Tutorial details: github.com/dglai/GML-on-M…

🎉 DiskGNN @SIGMODConf : Trained 300M+ node graphs (TB-scale) with just 1 GPU & <100GB RAM! Zero-overhead GPU/CPU/SSD pooling made it possible 🚀

* Consideration of the end-to-end process from tables to final predictions is critical to success." Paper link: arxiv.org/pdf/2404.18209 A collaborative effort by @AmazonScience DGL team, @sjtu1896 , @PKU1898 , @Tsinghua_Uni , @FudanUni , @CarnegieMellon and many (3/3)

Key findings from DBInfer-based comparisons of graph neural networks versus strong tabular baselines with feature engineering: * No single winner, a great open space for new models! * GNNs show the strongest performance, but the graph construction strategy matters too. (2/3)

Excited to release DBInfer, a comprehensive benchmarking toolbox for evaluating predictive modeling over relational DBs. The DBInfer-Bench package offers 14 benchmarks covering real-world scenarios like recsys, event forecasting, anomaly detection. Repo: github.com/awslabs/multi-…

DGL 2.1 with GPU-accelerated GraphBolt delivers blazing-fast data loading & stays flexible for customization. Plus, it works with PyTorch Geometric (PyG)! 👉Check out the blog for the release summary: dgl.ai/release/2024/0… 🧠Major Contributor: @mfbalin #DGL #GML

Say goodbye to data loading bottlenecks! DGL 2.0 introduces GraphBolt, a revolutionary data pipeline framework that supercharges your GNN training. 👉Check out the blog for the release summary: dgl.ai/release/2024/0…

Accelerating GNN Training on Intel CPU with DGL through fused sampling & hybrid partitioning, which can give you up to a 2x speedup! 🚀🧠 Awesome work done by Hesham (linkedin.com/in/hesham-most…) and Adam (linkedin.com/in/adam-grabow…). @IntelAI @IntelBusiness community.intel.com/t5/Blogs/Tech-…

Amazon has publicly released RefChecker, a combination tool and dataset that detects hallucinations in #LLMs. To characterize factual claims, RefChecker uses knowledge triplets rather than natural language, enabling finer-grained judgments. #GenerativeAI amazon.science/blog/new-tool-…

Project GitHub: github.com/amazon-science… Demo: github.com/amazon-science… (2/2)

Knowledge graph still rocks in the LLM era! Here is BSChecker🕵️, a new tool leveraging knowledge triplets to flag fine-grain hallucination of LLMs responses in zero/noise/accurate contexts. Demo and Github links below 👇 (1/2)

DGL team will be joining @LogConference Shanghai local meet-up to share our recent development. Event link: eventbrite.com/e/learning-on-… log2023sh.github.io . Find out more LoG local meet-ups nearby in the reply 👇

Will give a talk tomorrow Sunday 10am at the workshop Graph Learning Benchmarks @GLB_Workshop #KDD2023 w/ @YizhouSun, @jimeng, Z. Da @DGLGraph, A. Wang deep-learning-graphs.bitbucket.io/dlg-kdd23 Thanks to the organizers! Also glad to meet and chat about research during the conference 😀

Da Zheng @DGLGraph "Graph machine learning for industry applications with DGL and GraphStorm" #KDD2023

A new offering from the team! Announcing GraphStorm, a low-code framework for enterprise-level graph machine learning. See how it empowers GML in business 👇aws.amazon.com/blogs/machine-…

If new with graph learning, here is a warm-up notebook to learn to use graphs: • Build graph w/ features and compute basic message-passing function w/ @DGLGraph • Convert into graph formats w/ DGL, NetworkX, dense/sparse PyTorch • Visualize graph Code: github.com/xbresson/CS620…

Ever wanted to code Graph Transformer (GT) from *scratch* using a few lines of code with @PyTorch and @DGLGraph? :) See below my course material Slides: dropbox.com/s/i9coadk7fgzf… GitHub: github.com/xbresson/CS620… Paper: arxiv.org/pdf/2012.09699… Coding GT step-by-step 👇

For more information, check out the tutorial page github.com/dglai/Thewebco… or join our slack slack.dgl.ai channel "webconf23-tutorial".

Interested in DGL v1.0? Wanna try out the new sparse APIs for Graph ML? The team will host an hands-on tutorial @TheWebConf'23 on May 1st 1:30pm. Join us! #WWW23 #TheWebConf Video teaser: youtube.com/watch?v=8Zmxnk…