Papers › Self-supervised Feature-Gate Coupling for Dynamic Network Pruning

Self-supervised Feature-Gate Coupling for Dynamic Network Pruning

29 Nov 2021arXiv:2111.14302archive 2025-07-28

Mengnan Shi, Chang Liu, Jianbin Jiao, Qixiang Ye

Gating modules have been widely explored in dynamic network pruning to reduce the run-time computational cost of deep neural networks while preserving the representation of features. Despite the substantial progress, existing methods remain ignoring the consistency between feature and gate distributions, which may lead to distortion of gated features. In this paper, we propose a feature-gate coupling (FGC) approach aiming to align distributions of features and gates. FGC is a plug-and-play module, which consists of two steps carried out in an iterative self-supervised manner. In the first step, FGC utilizes the k-Nearest Neighbor method in the feature space to explore instance neighborhood relationships, which are treated as self-supervisory signals. In the second step, FGC exploits contrastive learning to regularize gating modules with generated self-supervisory signals, leading to the alignment of instance neighborhood relationships within the feature and gate spaces. Experimental results validate that the proposed FGC method improves the baseline approach with significant margins, outperforming the state-of-the-arts with better accuracy-computation trade-off. Code is publicly available.

PaperPDFCode

Code

smn2010/fgc-pr officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Contrastive LearningNetwork Pruning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Contrastive LearningPruning

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections