paper-with-me

홈 › Papers

Comment on "A Note on Over-Smoothing for Graph Neural Networks"

2025-09-04 · Razi Hasson, Reuven Guetta arxiv

We comment on Cai and Wang (2020, arXiv:2006.13318), who analyze over-smoothing in GNNs via Dirichlet energy. We show that under mild spectral conditions (including with Leaky-ReLU), the Dirichlet energy of node embeddings decreases exponentially with depth; we further extend the result to spectral polynomial filters and provide a short proof for the Leaky-ReLU case. Experiments on edge deletion and weight amplification illustrate when Dirichlet energy increases, hinting at practical ways to relieve over-smoothing.

📄 PDF Abstract BibTeX arXiv:2509.04178

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

A Note on Over-Smoothing for Graph Neural Networks

2020-06-23 · Chen Cai, Yusu Wang

Graph Neural Networks (GNNs) have achieved a lot of success on graph-structured data. However, it is observed that the performance of graph neural networks does not improve as the number of layers increases. This effect,…

Graph Neural Network

Digging Up Citations: FOSSIL, a Dataset and Workflow for Reference Extraction in Law and the Humanities

2026-05-31 · Luca Foppiano, Christian Boulanger arxiv

Citation extraction tools are designed for the structured end-of-document bibliographies of the natural sciences, but law and humanities scholarship cites references primarily in footnotes, where bibliographic data is in…

Creating Corpora for Research in Feedback Comment Generation

2020-05-01 · LREC 2020 5 · Ryo Nagata, Kentaro Inui, Shin{'}ichiro Ishikawa

In this paper, we report on datasets that we created for research in feedback comment generation {---} a task of automatically generating feedback comments such as a hint or an explanatory note for writing learning. Ther…

Comment Generation

Long-range Meta-path Search on Large-scale Heterogeneous Graphs

2023-07-17 · Chao Li, Zijie Guo, Qiuting He, Hao Xu 외

Utilizing long-range dependency, a concept extensively studied in homogeneous graphs, remains underexplored in heterogeneous graphs, especially on large ones, posing two significant challenges: Reducing computational cos…

Node ClassificationNode Property Prediction

Predicting the Understandability of Computational Notebooks through Code Metrics Analysis

2024-06-16 · Mojtaba Mostafavi Ghahfarokhi, Alireza Asadi, Arash Asgari, Bardia Mohammadi 외

Computational notebooks are the primary coding tools for data scientists, but their code quality remains understudied and often poor. Given the importance of maintainability and reusability, enhancing code understandabil…