Robust Graph Representation Learning via Neural Sparsification

By Cheng Zheng, Bo Zong, Wei Cheng, Dongjin Song, Jingchao Ni, Wenchao Yu, Haifeng Chen. International Conference on Machine Learning, 2020

338 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/f357b515af59b9d60bfaedb8028633c9033ec708

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Jinghao Zhang
2. Qiang Liu
3. Yanqiao Zhu
4. Junchi Yan
5. Shu Wu
6. Liang Wang
7. Qitian Wu
8. Shuhui Wang

Citations in the corpus

• NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification (2023, background): “, [28, 52] focus on sparsifying input structures to promote robust representations.”
• Learning to Drop: Robust Graph Neural Network via Topological Denoising (2020, methodology): “ormances by using a complex architecture is not the main research point of this paper. We compare with most recent state-of-the-art sampling and sparsification methods, DropEdge [38] and NeuralSparse [56]. For GraphSage, we use the mean aggregation. We follow the experimental setting in [38] to perf”
• Mining Latent Structures for Multimedia Recommendation (2021, methodology): “There are three categories of GSL methods: metric learning [5, 22, 37], probabilistic modeling [8, 25, 48], and direct optimization approaches [9, 17, 42].”
• Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings (2020, unknown): “, low rank and sparsity) [14, 24, 65].”