paper-with-me

Papers

Node Dependent Local Smoothing for Scalable Graph Learning

2021-10-27 · NeurIPS 2021 12 · Wentao Zhang, Mingyu Yang, Zeang Sheng, Yang Li, Wen Ouyang, Yangyu Tao, Zhi Yang, Bin Cui

Recent works reveal that feature or label smoothing lies at the core of Graph Neural Networks (GNNs). Concretely, they show feature smoothing combined with simple linear regression achieves comparable performance with the carefully designed GNNs, and a simple MLP model with label smoothing of its prediction can outperform the vanilla GCN. Though an interesting finding, smoothing has not been well understood, especially regarding how to control the extent of smoothness. Intuitively, too small or too large smoothing iterations may cause under-smoothing or over-smoothing and can lead to sub-optimal performance. Moreover, the extent of smoothness is node-specific, depending on its degree and local structure. To this end, we propose a novel algorithm called node-dependent local smoothing (NDLS), which aims to control the smoothness of every node by setting a node-specific smoothing iteration. Specifically, NDLS computes influence scores based on the adjacency matrix and selects the iteration number by setting a threshold on the scores. Once selected, the iteration number can be applied to both feature smoothing and label smoothing. Experimental results demonstrate that NDLS enjoys high accuracy -- state-of-the-art performance on node classifications tasks, flexibility -- can be incorporated with any models, scalability and efficiency -- can support large scale graphs with fast training.

📄 PDF Abstract BibTeX arXiv:2110.14377

Code (1)

zwt233/ndls 공식 구현 pytorch

Tasks

Graph Learning

Methods 이 논문이 사용한 방법론

GCN A Graph Convolutional Network, or GCN, is an approach for semi-supervised learning on graph-structured data. It is based on an efficient variant of [convolutional neural…
Linear Regression Linear Regression is a method for modelling a relationship between a dependent variable and independent variables. These models can be fit with numerous approaches. The most…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Similar Papers 제목 키워드 기반

Scalable Deep Graph Clustering with Random-walk based Self-supervised Learning

2021-12-31 · Xiang Li, Dong Li, Ruoming Jin, Gagan Agrawal 외

Web-based interactions can be frequently represented by an attributed graph, and node clustering in such graphs has received much attention lately. Multiple efforts have successfully applied Graph Convolutional Networks …

ClusteringDeep ClusteringGPUGraph Clustering+2

ScaleGNN: Towards Scalable Graph Neural Networks via Adaptive High-order Neighboring Feature Fusion

2025-04-22 · Xiang Li, Jianpeng Qi, Haobing Liu, Yuan Cao 외

Graph Neural Networks (GNNs) have demonstrated impressive performance across diverse graph-based tasks by leveraging message passing to capture complex node relationships. However, when applied to large-scale real-world …

Computational EfficiencyGraph Learning

Dual Mamba for Node-Specific Representation Learning: Tackling Over-Smoothing with Selective State Space Modeling

2025-11-10 · Xin He, Yili Wang, Yiwei Dai, Xin Wang arxiv

Over-smoothing remains a fundamental challenge in deep Graph Neural Networks (GNNs), where repeated message passing causes node representations to become indistinguishable. While existing solutions, such as residual conn…

Representation Learning

LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNN

2026-08-10 · Killian Cressant, Pedro B. Velloso arxiv

Graph Neural Networks (GNNs) suffer from two fundamental limitations: over-smoothing, where node representations become indistinguishable with depth, and over-squashing, where long-range information is compressed through…

Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks

2021-02-12 · Yujun Yan, Milad Hashemi, Kevin Swersky, Yaoqing Yang 외

In node classification tasks, graph convolutional neural networks (GCNs) have demonstrated competitive performance over traditional methods on diverse graph data. However, it is known that the performance of GCNs degrade…

Node ClassificationNode Classification on Non-Homophilic (Heterophilic) Graphs