paper-with-me

홈 › Papers

Spectral Theory for Edge Pruning in Asynchronous Recurrent Graph Neural Networks

2025-02-23 · Nicolas Bessone

Graph Neural Networks (GNNs) have emerged as a powerful tool for learning on graph-structured data, finding applications in numerous domains including social network analysis and molecular biology. Within this broad category, Asynchronous Recurrent Graph Neural Networks (ARGNNs) stand out for their ability to capture complex dependencies in dynamic graphs, resembling living organisms' intricate and adaptive nature. However, their complexity often leads to large and computationally expensive models. Therefore, pruning unnecessary edges becomes crucial for enhancing efficiency without significantly compromising performance. This paper presents a dynamic pruning method based on graph spectral theory, leveraging the imaginary component of the eigenvalues of the network graph's Laplacian.

📄 PDF Abstract BibTeX arXiv:2502.17522

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

Spectral Pruning for Recurrent Neural Networks

2021-05-23 · Takashi Furuya, Kazuma Suetake, Koichi Taniguchi, Hiroyuki Kusumoto 외

Recurrent neural networks (RNNs) are a class of neural networks used in sequential tasks. However, in general, RNNs have a large number of parameters and involve enormous computational costs by repeating the recurrent st…

Edge-computing

Spectral Pruning: Compressing Deep Neural Networks via Spectral Analysis and its Generalization Error

2018-08-26 · Taiji Suzuki, Hiroshi Abe, Tomoya Murata, Shingo Horiuchi 외

Compression techniques for deep neural network models are becoming very important for the efficient execution of high-performance deep learning systems on edge-computing devices. The concept of model compression is also …

Edge-computingLearning TheoryModel Compression

Theory of the asynchronous state of structured rotator networks and its application to recurrent networks of excitatory and inhibitory units

2022-11-19 · Jonas Ranft, Benjamin Lindner

Recurrently coupled oscillators that are sufficiently heterogeneous and/or randomly coupled can show an asynchronous activity in which there are no significant correlations among the units of the network. The asynchronou…

Asynchronous Coagent Networks

2019-02-15 · ICML 2020 1 · James E. Kostas, Chris Nota, Philip S. Thomas

Coagent policy gradient algorithms (CPGAs) are reinforcement learning algorithms for training a class of stochastic neural networks called coagent networks. In this work, we prove that CPGAs converge to locally optimal p…

Hierarchical Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

AlphaPruning: Using Heavy-Tailed Self Regularization Theory for Improved Layer-wise Pruning of Large Language Models

2024-10-14 · Haiquan Lu, Yefan Zhou, Shiwei Liu, Zhangyang Wang 외

Recent work on pruning large language models (LLMs) has shown that one can eliminate a large number of parameters without compromising performance, making pruning a promising strategy to reduce LLM model size. Existing L…