Signal Collapse in One-Shot Pruning: When Sparse Models Fail to Distinguish Neural Representations

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Saikumar, Dhananjay, Varghese, Blesson
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

DRIVE: Dual Gradient-Based Rapid Iterative Pruning
by: Saikumar, Dhananjay, et al.
Published: (2024)

Data-Free Pruning of Self-Attention Layers in LLMs
by: Saikumar, Dhananjay, et al.
Published: (2025)

NeuroFlux: Memory-Efficient CNN Training Using Adaptive Local Learning
by: Saikumar, Dhananjay, et al.
Published: (2024)

A Closer Look at Multimodal Representation Collapse
by: Chaudhuri, Abhra, et al.
Published: (2025)

MaxSup: Overcoming Representation Collapse in Label Smoothing
by: Zhou, Yuxuan, et al.
Published: (2025)

When Rubrics Fail: Error Enumeration as Reward in Reference-Free RL Post-Training for Virtual Try-On
by: Ikezogwo, Wisdom, et al.
Published: (2026)

One-Shot Domain Incremental Learning
by: Esaki, Yasushi, et al.
Published: (2024)

Feature-Space Generative Models for One-Shot Class-Incremental Learning
by: Foster, Jack, et al.
Published: (2026)

Training-Free Restoration of Pruned Neural Networks
by: Lee, Keonho, et al.
Published: (2025)

One-Step is Enough: Sparse Autoencoders for Text-to-Image Diffusion Models
by: Surkov, Viacheslav, et al.
Published: (2024)

One-Cycle Structured Pruning via Stability-Driven Subnetwork Search
by: Ghimire, Deepak, et al.
Published: (2025)

1S-DAug: One-Shot Data Augmentation for Robust Few-Shot Generalization
by: Bai, Yunwei, et al.
Published: (2026)

Memory-efficient Continual Learning with Neural Collapse Contrastive
by: Dang, Trung-Anh, et al.
Published: (2024)

One-Shot Machine Unlearning with Mnemonic Code
by: Yamashita, Tomoya, et al.
Published: (2023)

A Markovian View of Iterative-Feedback Loops in Image Generative Models: Neural Resonance and Model Collapse
by: Vats, Vibhas Kumar, et al.
Published: (2026)

Steering Sparse Autoencoder Latents to Control Dynamic Head Pruning in Vision Transformers (Student Abstract)
by: Lee, Yousung, et al.
Published: (2026)

DMTG: One-Shot Differentiable Multi-Task Grouping
by: Gao, Yuan, et al.
Published: (2024)

Isomorphic Pruning for Vision Models
by: Fang, Gongfan, et al.
Published: (2024)

Few-Shot Unsupervised Implicit Neural Shape Representation Learning with Spatial Adversaries
by: Ouasfi, Amine, et al.
Published: (2024)

DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models
by: Alvar, Saeed Ranjbar, et al.
Published: (2025)

ConceptPrune: Concept Editing in Diffusion Models via Skilled Neuron Pruning
by: Chavhan, Ruchika, et al.
Published: (2024)

Disentangled Sparse Representations for Concept-Separated Diffusion Unlearning
by: Kim, Hyeonjin, et al.
Published: (2026)

MINR: Implicit Neural Representations with Masked Image Modelling
by: Lee, Sua, et al.
Published: (2025)

Automatic Joint Structured Pruning and Quantization for Efficient Neural Network Training and Compression
by: Qu, Xiaoyi, et al.
Published: (2025)

Do Sparse Subnetworks Exhibit Cognitively Aligned Attention? Effects of Pruning on Saliency Map Fidelity, Sparsity, and Concept Coherence
by: Suwal, Sanish, et al.
Published: (2025)

Learning Sparse Visual Representations via Spatial-Semantic Factorization
by: Zhao, Theodore Zhengde, et al.
Published: (2026)

PortraitTalk: Towards Customizable One-Shot Audio-to-Talking Face Generation
by: Nazarieh, Fatemeh, et al.
Published: (2024)

Beyond Interpretability: When, Why, and How Sparse Autoencoders Enable Label-Free Visual Steering
by: Chatzoudis, Gerasimos, et al.
Published: (2025)

MDP: Multidimensional Vision Model Pruning with Latency Constraint
by: Sun, Xinglong, et al.
Published: (2025)

Exploring Token Pruning in Vision State Space Models
by: Zhan, Zheng, et al.
Published: (2024)

Quantum Implicit Neural Representations
by: Zhao, Jiaming, et al.
Published: (2024)

B-SMALL: A Bayesian Neural Network approach to Sparse Model-Agnostic Meta-Learning
by: Madan, Anish, et al.
Published: (2021)

Pruning By Explaining Revisited: Optimizing Attribution Methods to Prune CNNs and Transformers
by: Hatefi, Sayed Mohammad Vakilzadeh, et al.
Published: (2024)

ACD-CLIP: Decoupling Representation and Dynamic Fusion for Zero-Shot Anomaly Detection
by: Ma, Ke, et al.
Published: (2025)

Zero-Shot Neural Architecture Search with Weighted Response Correlation
by: Jing, Kun, et al.
Published: (2025)

Informative Rays Selection for Few-Shot Neural Radiance Fields
by: Orsingher, Marco, et al.
Published: (2023)

Exploring Diffusion Models' Corruption Stage in Few-Shot Fine-tuning and Mitigating with Bayesian Neural Networks
by: Wu, Xiaoyu, et al.
Published: (2024)

OMENN: One Matrix to Explain Neural Networks
by: Wróbel, Adam, et al.
Published: (2024)

Multi-Dimensional Pruning: Joint Channel, Layer and Block Pruning with Latency Constraint
by: Sun, Xinglong, et al.
Published: (2024)

AdaRank: Adaptive Rank Pruning for Enhanced Model Merging
by: Lee, Chanhyuk, et al.
Published: (2025)