Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks

2019-06-05 · NeurIPS 2019 12 · Sitao Luan, Mingde Zhao, Xiao-Wen Chang, Doina Precup

Recently, neural network based approaches have achieved significant improvement for solving large, complex, graph-structured problems. However, their bottlenecks still need to be addressed, and the advantages of multi-scale information and deep architectures have not been sufficiently exploited. In this paper, we theoretically analyze how existing Graph Convolutional Networks (GCNs) have limited expressive power due to the constraint of the activation functions and their architectures. We generalize spectral graph convolution and deep GCN in block Krylov subspace forms and devise two architectures, both with the potential to be scaled deeper but each making use of the multi-scale information in different ways. We further show that the equivalence of these two architectures can be established under certain conditions. On several node classification tasks, with or without the help of validation, the two new architectures achieve better performance compared to many state-of-the-art methods.

📄 PDF Abstract BibTeX arXiv:1906.02174

Code (1)

PwnerHarry/Stronger_GCN 공식 구현 pytorch

Tasks

Node Classification Node Classification on Non-Homophilic (Heterophilic) Graphs

Methods 이 논문이 사용한 방법론

Graph Convolutional Networks 설명 없음

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

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…

MAD-OPD: Breaking the Ceiling in On-Policy Distillation via Multi-Agent Debate

2026-05-02 · Jianze Wang, Ying Liu, Jinlong Chen, Xuchun Hu 외 arxiv

On-policy distillation (OPD) trains a student on its own trajectories under token-level teacher supervision, but existing methods are capped by a single-teacher capability ceiling: when the teacher errs, the student inhe…

Code Generation

Breaking Through the 80\% Glass Ceiling: Raising the State of the Art in Word Sense Disambiguation by Incorporating Knowledge Graph Information

2020-07-01 · ACL 2020 6 · Michele Bevilacqua, Roberto Navigli

Neural architectures are the current state of the art in Word Sense Disambiguation (WSD). However, they make limited use of the vast amount of relational information encoded in Lexical Knowledge Bases (LKB). We present E…

All Word Sense Disambiguation

Generalizing GNNs with Tokenized Mixture of Experts

2026-02-09 · Xiaoguang Guo, Zehong Wang, Jiazheng Li, Shawn Spitzel 외 arxiv

Deployed graph neural networks (GNNs) are frozen at deployment yet must fit clean data, generalize under distribution shifts, and remain stable to perturbations. We show that static inference induces a fundamental tradeo…

Breaking the Performance Ceiling in Complex Reinforcement Learning requires Inference Strategies

2025-05-27 · Felix Chalumeau, Daniel Rajaonarivonivelomanantsoa, Ruan de Kock, Claude Formanek 외

Reinforcement learning (RL) systems have countless applications, from energy-grid management to protein design. However, such real-world scenarios are often extremely difficult, combinatorial in nature, and require compl…

Protein Design Reinforcement Learning (RL)

SHAPE: Unifying Safety, Helpfulness and Pedagogy for Educational LLMs

2026-04-24 · Sihang Zhao, Kangrui Yu, Youliang Yuan, Pinjia He 외 arxiv

Large Language Models (LLMs) have been widely explored in educational scenarios. We identify a critical vulnerability in current educational LLMs, pedagogical jailbreaks, where students use answer-inducing prompts to eli…