paper-with-me

홈 › Papers

Topological Signatures of ReLU Neural Network Activation Patterns

2025-10-14 · Vicente Bosca, Tatum Rask, Sunia Tanweer, Andrew R. Tawfeek, Branden Stone arxiv

This paper explores the topological signatures of ReLU neural network activation patterns. We consider feedforward neural networks with ReLU activation functions and analyze the polytope decomposition of the feature space induced by the network. Mainly, we investigate how the Fiedler partition of the dual graph and show that it appears to correlate with the decision boundary -- in the case of binary classification. Additionally, we compute the homology of the cellular decomposition -- in a regression task -- to draw similar patterns in behavior between the training loss and polyhedral cell-count, as the model is trained.

📄 PDF Abstract BibTeX arXiv:2510.12700

Code (0)

등록된 구현이 없습니다.

Tasks

Binary Classification

Similar Papers 제목 키워드 기반

Deep ReLU Networks Have Surprisingly Few Activation Patterns

2019-06-03 · NeurIPS 2019 12 · Boris Hanin, David Rolnick

The success of deep networks has been attributed in part to their expressivity: per parameter, deep networks can approximate a richer class of functions than shallow networks. In ReLU networks, the number of activation p…

Memorization

Data Topology-Dependent Upper Bounds of Neural Network Widths

2023-05-25 · Sangmin Lee, Jong Chul Ye

This paper investigates the relationship between the universal approximation property of deep neural networks and topological characteristics of datasets. Our primary contribution is to introduce data topology-dependent …

Beyond ReLU: Bifurcation, Oversmoothing, and Topological Priors

2026-02-17 · Erkan Turan, Gaspard Abel, Maysam Behmanesh, Emery Pierson 외 arxiv

Graph Neural Networks (GNNs) learn node representations through iterative network-based message-passing. While powerful, deep GNNs suffer from oversmoothing, where node features converge to a homogeneous, non-informative…

Topological obstruction to the training of shallow ReLU neural networks

2024-10-18 · Marco Nurisso, Pierrick Leroy, Francesco Vaccarino

Studying the interplay between the geometry of the loss landscape and the optimization trajectories of simple neural networks is a fundamental step for understanding their behavior in more complex settings. This paper re…

ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models

2023-10-06 · Iman Mirzadeh, Keivan Alizadeh, Sachin Mehta, Carlo C Del Mundo 외

Large Language Models (LLMs) with billions of parameters have drastically transformed AI applications. However, their demanding computation during inference has raised significant challenges for deployment on resource-co…