paper-with-me

Papers

Feature Overcorrelation in Deep Graph Neural Networks: A New Perspective

2022-06-15 · Wei Jin, Xiaorui Liu, Yao Ma, Charu Aggarwal, Jiliang Tang

Recent years have witnessed remarkable success achieved by graph neural networks (GNNs) in many real-world applications such as recommendation and drug discovery. Despite the success, oversmoothing has been identified as one of the key issues which limit the performance of deep GNNs. It indicates that the learned node representations are highly indistinguishable due to the stacked aggregators. In this paper, we propose a new perspective to look at the performance degradation of deep GNNs, i.e., feature overcorrelation. Through empirical and theoretical study on this matter, we demonstrate the existence of feature overcorrelation in deeper GNNs and reveal potential reasons leading to this issue. To reduce the feature correlation, we propose a general framework DeCorr which can encourage GNNs to encode less redundant information. Extensive experiments have demonstrated that DeCorr can help enable deeper GNNs and is complementary to existing techniques tackling the oversmoothing issue.

📄 PDF Abstract BibTeX arXiv:2206.07743

Code (1)

chandlerbang/decorr 공식 구현 pytorch

Tasks

Drug DiscoveryFeature Correlation

Similar Papers 제목 키워드 기반

Towards Feature Overcorrelation in Deeper Graph Neural Networks

2021-09-29 · Wei Jin, Xiaorui Liu, Yao Ma, Charu Aggarwal 외

Graph neural networks (GNNs) have achieved great success in graph representation learning, which has tremendously facilitated various real-world applications. Nevertheless, the performance of GNNs significantly deteriora…

Feature CorrelationGraph Representation LearningRepresentation Learning

Response to Promises and Pitfalls of Deep Kernel Learning

2025-09-25 · Andrew Gordon Wilson, Zhiting Hu, Ruslan Salakhutdinov, Eric P. Xing arxiv

This note responds to "Promises and Pitfalls of Deep Kernel Learning" (Ober et al., 2021). The marginal likelihood of a Gaussian process can be compartmentalized into a data fit term and a complexity penalty. Ober et al.…

MMPG: MoE-based Adaptive Multi-Perspective Graph Fusion for Protein Representation Learning

2026-01-15 · Yusong Wang, Jialun Shen, Zhihao Wu, Yicheng Xu 외 arxiv

Graph Neural Networks (GNNs) have been widely adopted for Protein Representation Learning (PRL), as residue interaction networks can be naturally represented as graphs. Current GNN-based PRL methods typically rely on sin…

Representation Learning

Modeling Human Perspectives with Socio-Demographic Representations

2026-04-20 · Leixin Zhang, Cagri Coltekin arxiv

Humans often hold different perspectives on the same issues. In many NLP tasks, annotation disagreement can reflect valid subjective perspectives. Modeling annotator perspectives and understanding their relationship with…

Contrastive Learning

Single-Perspective Warps in Natural Image Stitching

2018-02-13 · Tianli Liao, Nan Li

Results of image stitching can be perceptually divided into single-perspective and multiple-perspective. Compared to the multiple-perspective result, the single-perspective result excels in perspective consistency but su…

Image Stitching