I have written some paper notes before, but I probably won't update them here anymore.

- [NeurIPS 2021] Dirichlet Energy Constrained Learning for Deep Graph Neural Networks [Paper | Note]
- [WWW 2021] On the Equivalence of Decoupled Graph Convolution Network and Label Propagation [Paper | Note]
- [WSDM 2020] All You Need Is Low (Rank): Defending Against Adversarial Attacks on Graphs [Paper | Note]
- [ICML 2019] Learning Discrete Structures for Graph Neural Networks [Paper | Note]
- [arXiv 2022] Asynchronous Neural Networks for Learning in Graphs [Paper | Note]
- [arXiv 2022] Learning Graph Structure from Convolutional Mixtures [Paper | Note]
- [arXiv 2022] GARNET: Reduced-Rank Topology Learning for Robust and Scalable Graph Neural Networks [Paper | Note]
- [arXiv 2022] Alternately Optimized Graph Neural Networks [Paper | Note]
- [ICML 2021] Graph Neural Networks Inspired by Classical Iterative Algorithms [Paper | Note]
- [WSDM 2021] Learning to Drop Robust Graph Neural Network via Topological Denoising [Paper | Note]
- [ECML-PKDD 2021] Graph-Revised Convolutional Network [Paper | Note]
- [ICML 2022] Finding Global Homophily in Graph Neural Networks When Meeting Heterophily [Paper | Note]
- [arXiv 2022] GPN: A Joint Structural Learning Framework for Graph Neural Networks [Paper | Note]
- [NeurIPS 2021] Building Powerful and Equivariant Graph Neural Networks with Structural Message-Passing [Paper | Note]
- [NeurIPS 2021] Not All Low-Pass Filters are Robust in Graph Convolutional Networks [Paper | Note]
- [ICLR-GTRL 2022] Diversified Multiscale Graph Learning with Graph Self-Correction [Paper | Note]
- [NeurIPS 2020] Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings [Paper | Note]
- [WWW 2022] Towards Unsupervised Deep Graph Structure Learning [Paper | Note]
- [IJCAI 2022] Fine-Tuning Graph Neural Networks via Graph Topology induced Optimal Transport [Paper | Note]
- [arXiv 2022] Hypergraph Convolutional Networks via Equivalency between Hypergraphs and Undirected Graphs [Paper | Note]
- [IJCAI 2021] On Self-Distilling Graph Neural Network [Paper | Note]
- [arXiv 2022] FMP: Toward Fair Graph Message Passing against Topology Bias [Paper | Note]
- [NeurIPS 2021] SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networks [Paper | Note ]
- [ICML 2022] p-Laplacian Based Graph Neural Networks [Paper | Note]
- [NeurIPS 2020] Self-Supervised Graph Transformer on Large-Scale Molecular Data [Paper | Note]