paper-with-me

홈 › Papers

Drawback of Enforcing Equivariance and its Compensation via the Lens of Expressive Power

2025-12-10 · Yuzhu Chen, Tian Qin, Xinmei Tian, Fengxiang He, Dacheng Tao arxiv

Equivariant neural networks encode the intrinsic symmetry of data as an inductive bias, which has achieved impressive performance in wide domains. However, the understanding to their expressive power remains premature. Focusing on 2-layer ReLU networks, this paper investigates the impact of enforcing equivariance constraints on the expressive power. By examining the boundary hyperplanes and the channel vectors, we constructively demonstrate that enforcing equivariance constraints could undermine the expressive power. Naturally, this drawback can be compensated for by enlarging the model size -- we further prove upper bounds on the required enlargement for compensation. Surprisingly, we show that the enlarged neural architectures have reduced hypothesis space dimensionality, implying even better generalizability.

📄 PDF Abstract BibTeX arXiv:2512.09673

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

A Clifford Algebraic Approach to E(n)-Equivariant High-order Graph Neural Networks

2024-10-07 · Viet-Hoang Tran, Thieu N. Vo, Tho Tran Huu, Tan Minh Nguyen

Designing neural network architectures that can handle data symmetry is crucial. This is especially important for geometric graphs whose properties are equivariance under Euclidean transformations. Current equivariant gr…

Flock: A Knowledge Graph Foundation Model via Learning on Random Walks

2025-10-01 · Jinwoo Kim, Xingyue Huang, Krzysztof Olejniczak, Kyungbin Min 외 arxiv

We study the problem of zero-shot link prediction on knowledge graphs (KGs), which requires models to generalize to novel entities and novel relations. Knowledge graph foundation models (KGFMs) address this task by enfor…

Knowledge GraphsLink Prediction

Harmonizing SO(3)-Equivariance with Neural Expressiveness: a Hybrid Deep Learning Framework Oriented to the Prediction of Electronic Structure Hamiltonian

2024-01-01 · Shi Yin, Xinyang Pan, XUDONG ZHU, Tianyu Gao 외

Deep learning for predicting the electronic structure Hamiltonian of quantum systems necessitates satisfying the covariance laws, among which achieving SO(3)-equivariance without sacrificing the non-linear expressive cap…

Navigateregression

Blind Detection and Compensation of Camera Lens Geometric Distortions

2004-05-25 · Lili Ma, YangQuan Chen, Kevin L. Moore

This paper presents a blind detection and compensation technique for camera lens geometric distortions. The lens distortion introduces higher-order correlations in the frequency domain and in turn it can be detected usin…

Ray-Space Motion Compensation for Lenslet Plenoptic Video Coding

2022-07-01 · Thuc Nguyen Huu, Vinh Van Duong, Jonghoon Yim, Byeungwoo Jeon

Plenoptic images and videos bearing rich information demand a tremendous amount of data storage and high transmission cost. While there has been much study on plenoptic image coding, investigations into plenoptic video c…

Motion Compensation