😄Remind myself not to miss any related papers

Rewiring-strategy-for-heterophily

☑️[Arxiv 2022] Make Heterophily Graphs Better Fit GNN: A Graph Rewiring Approach.paper
⭐[ICLR 2022] Understanding over-squashing and bottlenecks on graphs via curvature.paper
⭐[WWW 2023] Homophily-oriented Heterogeneous Graph Rewiring.paper
⭐[AAAI 2023] Restructuring Graph for Higher Homophily via Adaptive Spectral Clustering.paper
⭐[ICML 2023] Finding the Missing-half: Graph Complementary Learning for Homophily-prone and Heterophily-prone Graphs.paper

Graph Structure Learning methods: make adjacency matrix a learnable parameter:

☑️[IEEE-ICME 2020]Exploring structure-adaptive graph learning for robust semi-supervised classification.paper
☑️[AAAI 2021]Graph Sparsification via Meta-Learning.paper
☑️[AAAI2021]Heterogeneous Graph Structure Learning for Graph Neural Networks.paper[code] (https://github.com/AndyJZhao/HGSL)
⭐[ACM 2024]MHGCN+: Multiplex Heterogeneous Graph Convolutional Network. paper
⭐[IEEE 2024]A Fast and Robust Attention-free Heterogeneous Graph Convolutional Network.paper
⭐SELECTOR: Heterogeneous graph network with convolutional masked autoencoder for multimodal robust prediction of cancer survival.paper
⭐Heterophilic Graph Neural Network Based on Spatial and Frequency Domain Adaptive Embedding Mechanism.paper
⭐[IEEE 2023]Heterogeneous Graph Neural Network Based on Hierarchical Attention Mechanism.paper

Graph Structure Learning methods: use a bilevel optimization pipeline

⭐Deep Graph Structure Learning for Robust Representations: A Survey.paper
☑️[ICML 2019]Learning discrete structures for graph neural networks.paper
⭐[NIPS 2020]Iterative deep graph learning for graph neural networks: Better and robust node embeddings.paper

High pass filter in heterophily graph

☑️[AAAI 2021]Beyond Low-frequency Information in Graph Convolutional Networks.paper code
☑️[NIPS 2022]Revisiting Heterophily For Graph Neural Networks.paper code
⭐[ICLR 2023]The official implementation of the paper "Ordered GNN: Ordering Message Passing to Deal with Heterophily and Over-smoothing".paper code

With degree imbalance

⭐DAHGN: Degree-Aware Heterogeneous Graph Neural Network.paper