graph-learning

A distributed graph deep learning framework.

Paddle Graph Learning (PGL) is an efficient and flexible graph learning framework based on PaddlePaddle

High performance, easy-to-use, and scalable package for learning large-scale knowledge graph embeddings.

Training neural models with structured signals.

[SIGIR'2024] "GraphGPT: Graph Instruction Tuning for Large Language Models"

Code for the paper "PICK: Processing Key Information Extraction from Documents using Improved Graph Learning-Convolutional Networks" (ICPR 2020)

[WSDM'2024 Oral] "LLMRec: Large Language Models with Graph Augmentation for Recommendation"

[EMNLP'2024] "OpenGraph: Towards Open Graph Foundation Models"

PyTorch Library for Low-Latency, High-Throughput Graph Learning on GPUs.

Extensible Surrogate Potential of Ab initio Learned and Optimized by Message-passing Algorithm 🍹https://arxiv.org/abs/2010.01196

Code & data accompanying the NeurIPS 2020 paper "Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings".

"AnyGraph: Graph Foundation Model in the Wild"

Advances on machine learning of graphs, covering the reading list of recent top academic conferences.

A Tensorflow implementation of "Bayesian Graph Convolutional Neural Networks" (AAAI 2019).

A curated list of resources on cold-start recommendations.

A real-world dataset for EV-related research, e.g., spatiotemporal prediction and urban energy management.

An SDK for multi-agent collaborative perception.

Neuro-symbolic interpretation learning (mostly just language-learning, for now)

[NeurIPS2021] Learning Distilled Collaboration Graph for Multi-Agent Perception

Code for the SIGGRAPH 2022 paper "DeltaConv: Anisotropic Operators for Geometric Deep Learning on Point Clouds."