yifeiacc / COSTA
Code for KDD'22 paper, COSTA: Covariance-Preserving Feature Augmentation for Graph Contrastive Learning
☆48Updated last year
Alternatives and similar repositories for COSTA:
Users that are interested in COSTA are comparing it to the libraries listed below
- [AAAI'23] Beyond Smoothing: Unsupervised Graph Representation Learning with Edge Heterophily Discriminating☆50Updated 2 years ago
- Source code for NeurIPS 2022 paper "Uncovering the Structural Fairness in Graph Contrastive Learning"☆29Updated 2 years ago
- Official Code: TheWebConf 2022 Compact Graph Structure Learning via Mutual Information Compression☆24Updated 10 months ago
- ICML 2022, Finding Global Homophily in Graph Neural Networks When Meeting Heterophily☆42Updated 2 years ago
- The code Implementation of the paper “Universal Prompt Tuning for Graph Neural Networks”.☆25Updated last year
- "GraphSHA: Synthesizing Harder Samples for Class-Imbalanced Node Classification" in KDD'23☆29Updated 10 months ago
- Codes for 'From Canonical Correlation Analysis to Self-supervised Graph Neural Networks'. https://arxiv.org/abs/2106.12484☆68Updated last year
- [WSDM'23] GOOD-D: On Unsupervised Graph Out-Of-Distribution Detection☆37Updated last year
- [NeurIPS 2023] "Unleashing the Power of Graph Data Augmentation on Covariate Distribution Shift" by Yongduo Sui, Qitian Wu, Jiancan Wu, Q…☆16Updated last year
- Official repository for ICLR'23 paper: Multi-task Self-supervised Graph Neural Network Enable Stronger Task Generalization☆37Updated last year
- The code Implementation of the paper “Universal Prompt Tuning for Graph Neural Networks”.☆20Updated last year
- An official PyTorch implementation of "Towards Robust Graph Neural Networks for Noisy Graphs with Sparse Labels" (WSDM 2022))☆32Updated 2 years ago
- GraphACL: Simple and Asymmetric Graph Contrastive Learning (NeurIPS 2023)☆28Updated 7 months ago
- Code for "Graph Structure Learning with Variational Information Bottleneck" published in AAAI 2022☆33Updated 2 years ago
- [NeurIPS 2022] "Augmentations in Hypergraph Contrastive Learning: Fabricated and Generative" by Tianxin Wei, Yuning You, Tianlong Chen, Y…☆54Updated 2 years ago
- Code for ECML-PKDD 2022 paper "GraphMixup: Improving Class-Imbalanced Node Classification by Reinforcement Mixup and Self-supervised Cont…☆22Updated last year
- Code for NeurIPS 2022 paper "Rethinking and Scaling Up Graph Contrastive Learning: An Extremely Efficient Approach with Group Discriminat…☆54Updated last year
- The Open Source Code For ICML 2023 Paper "Finding the Missing-half: Graph Complementary Learning for Homophily-prone and Heterophily-pron…☆15Updated last year
- The source code of SpCo☆34Updated last year
- Source code for WWW 2021 paper "Graph Structure Estimation Neural Networks"☆58Updated 3 years ago
- NeurIPS 2022, Revisiting Heterophily For Graph Neural Networks, official PyTorch implementation for Adaptive Channel Mixing (ACM) GNN fra…☆77Updated last month
- Code for The Web Conference 2022 Paper "Collaborative Knowledge Distillation for Heterogeneous Information Network Embedding"☆16Updated 2 years ago
- [WSDM 2023] "Alleviating Structrual Distribution Shift in Graph Anomaly Detection" by Yuan Gao, Xiang Wang, Xiangnan He, Zhenguang Liu, H…☆20Updated last year
- The official source code for "LTE4G: Long-Tail Experts for Graph Neural Networks" paper, accepted at CIKM 2022.☆38Updated 2 years ago
- [KDD 2022] Implementation of "Feature Overcorrelation in Deep Graph Neural Networks: A New Perspective"☆45Updated last year
- This is the repository for the AAAI 21 paper [Contrastive and Generative Graph Convolutional Networks for Graph-based Semi-Supervised Lea…☆17Updated last year
- Comprehensive Benchmark Dataset for Dynamic Text-Attributed Graphs☆28Updated 2 months ago
- A collection of papers on Graph Structural Learning (GSL)☆54Updated last year
- [ICML 2022] "ProGCL: Rethinking Hard Negative Mining in Graph Contrastive Learning"☆45Updated 2 years ago
- Code & data for ICLR'23 Spotlight paper "Learning MLPs on Graphs: A Unified View of Effectiveness, Robustness, and Efficiency".☆31Updated last year