关于图神经网络(GNN)预训练和自监督学习的论文。
graph-self-supervised-learning 开源项目推荐(12 个)
graph-self-supervised-learning 话题在 GitHub 上没有填写简介,这里按 Star 数汇总最相关的热门仓库。
热门项目 全部 12
GitHub 共 12 个仓库,已全部展示[WWW 2022] "SimGRACE: A Simple Framework for Graph Contrastive Learning without Data Augmentation"
[TKDE 2021] A PyTorch implementation of "Generative and Contrastive Self-Supervised Learning for Graph Anomaly Detection".
[ICML 2022] "ProGCL: Rethinking Hard Negative Mining in Graph Contrastive Learning"
[IJCAI 2021] A PyTorch implementation of "Multi-Scale Contrastive Siamese Networks for Self-Supervised Graph Representation Learning".
Papers about Graph Contrastive Learning and Graph Self-supervised Learning on Graphs with Heterophily
Code for ECML-PKDD 2022 paper "GraphMixup: Improving Class-Imbalanced Node Classification by Reinforcement Mixup and Self-supervised Context Prediction"
Source code of NeurIPS 2022 paper “Co-Modality Graph Contrastive Learning for Imbalanced Node Classification”
Code for ECML-PKDD 2023 paper "Learning to Augment Graph Structure for both Homophily and Heterophily Graphs"
GraphSSL-MultiCancer-GFM: Graph Self-Supervised Pretraining on 20 Cancers (TCGA/METABRIC) with ESM-2 Protein LM. Cell Reports Methods (Methods Track) Reproduction Package. FDA Schuirmann-1987 TOST Δ₀=0.002 EQUIVALENT.
[Preprint]Official Code of our paper Predict, Cluster, Refine: A Joint Embedding Predictive Self-Supervised Framework for Graph Representation Learning
Disentangle music audio into independent melody, rhythm, and timbre signals to compute precise multi-factor similarity scores.
关于这个话题
- 清单取自 GitHub 话题页并按 Star 数排序,每次展示前 12 个项目;原始页面见 https://github.com/topics/graph-self-supervised-learning。
- 该话题在 GitHub 上共有 12 个仓库, 本站收录的是其中最热门的 12 个,不是全量列表。
- Star / Fork 每日自动刷新一次,实时数据以 GitHub 为准。
- 当前 12 个项目累计 2040 Star,覆盖 2 种主要语言,数据更新于 2026-11-13。
- 中文介绍来自 GitHub 官方话题说明(github/explore)的机器翻译,可点「查看原文」对照;译文缺失时会先展示原文。