Papers Network Pruning
“Network Pruning” 태그가 달린 논문 569편 · 필터 해제
CutClean: Neural Network Pruning for Privacy-Preserving Inference
Neural networks are increasingly deployed in high-stakes applications with growing privacy leakage concerns. We show that this privacy leakage can occur even in the absence of representation imbalances that lead to tradi…
Network PruningFinding Sparse Subnetworks in One Training Cycle via Progressive Magnitude-Based Pruning
Neural network pruning reduces model size by removing less important parameters while aiming to preserve predictive performance. Although the Lottery Ticket Hypothesis (LTH) shows that sparse subnetworks can match dense …
Network PruningRelative Repairability: A Calibration-Based Diagnostic for High-Sparsity Post-Pruning Allocation
At very high sparsity, neural network pruning does more than decide which weights remain. It also determines where pruning induced damage is placed across the network, and whether that damage can be recovered by a fixed …
Network PruningSelection Plateau and a Sparsity-Dependent Hierarchy of Pruning Features
We identify a Selection Plateau phenomenon in one-shot neural network pruning: all rank-monotone weight scorers converge to identical accuracy at fixed sparsity, independent of functional form. We propose the Sparsity-In…
Network PruningGraph Normalization: Fast Binarizing Dynamics for Differentiable MWIS
We introduce Graph Normalization (GN), a principled dynamical system on graphs that serves as a differentiable approximation engine for the NP-hard Maximum Weight Independent Set (MWIS) problem. MWIS encompasses many com…
Network PruningSubFLOT: Submodel Extraction for Efficient and Personalized Federated Learning via Optimal Transport
Federated Learning (FL) enables collaborative model training while preserving data privacy, but its practical deployment is hampered by system and statistical heterogeneity. While federated network pruning offers a path …
Personalized Federated LearningNetwork PruningCross-Resolution Diffusion Models via Network Pruning
Diffusion models have demonstrated impressive image synthesis performance, yet many UNet-based models are trained at certain fixed resolutions. Their quality tends to degrade when generating images at out-of-training res…
Network PruningNeural Network Pruning via QUBO Optimization
Neural network pruning can be formulated as a combinatorial optimization problem, yet most existing approaches rely on greedy heuristics that ignore complex interactions between filters. Formal optimization methods such …
Neural Network CompressionImage DenoisingNetwork PruningSLaB: Sparse-Lowrank-Binary Decomposition for Efficient Large Language Models
The rapid growth of large language models (LLMs) presents significant deployment challenges due to their massive computational and memory demands. While model compression, such as network pruning, offers potential soluti…
Model CompressionNetwork PruningA Hierarchical Importance-Guided Multi-objective Evolutionary Framework for Deep Neural Network Pruning
The optimization of over-parameterized deep neural networks represents a large-scale, high-dimensional, and strongly non-convex decision problem that challenges existing optimization frameworks. Current evolutionary and …
Network PruningDemystifying When Pruning Works via Representation Hierarchies
Network pruning, which removes less important parameters or architectures, is often expected to improve efficiency while preserving performance. However, this expectation does not consistently hold across language tasks:…
Network PruningFlash-Unified: A Training-Free and Task-Aware Acceleration Framework for Native Unified Models
Native unified multimodal models, which integrate both generative and understanding capabilities, face substantial computational overhead that hinders their real-world deployment. Existing acceleration techniques typical…
Image GenerationNetwork PruningMostly Text, Smart Visuals: Asymmetric Text-Visual Pruning for Large Vision-Language Models
Network pruning is an effective technique for enabling lightweight Large Vision-Language Models (LVLMs), which primarily incorporates both weights and activations into the importance metric. However, existing efforts typ…
Network PruningCausal Mechanism Reduction: Mechanism Replacement for Neural Network Pruning and Abstraction
Which internal mechanisms of a neural network can be replaced while preserving the computation it performs? Structured pruning asks for smaller deployable networks; causal abstraction asks for high-level models that comm…
Network PruningUnlearning Noise in PINNs: A Selective Pruning Framework for PDE Inverse Problems
Physics-informed neural networks (PINNs) provide a promising framework for solving inverse problems governed by partial differential equations (PDEs) by integrating observational data and physical constraints in a unifie…
Network PruningPost-Training Neural Network Pruning using Graph Curvature
This paper provides a fresh view of the neural network (NN) pruning problem through the lens of graph theory. To achieve effective pruning, we aim to identify the main NN data flows and the corresponding NN connections t…
Network PruningAgenticPruner: MAC-Constrained Neural Network Compression via LLM-Driven Strategy Search
Neural network pruning remains essential for deploying deep learning models on resource-constrained devices, yet existing approaches primarily target parameter reduction without directly controlling computational cost. T…
Neural Network CompressionNetwork PruningMeta-Learning Guided Pruning for Few-Shot Plant Pathology on Edge Devices
Farmers in remote areas need quick and reliable methods for identifying plant diseases, yet they often lack access to laboratories or high-performance computing resources. Deep learning models can detect diseases from le…
Few-Shot LearningNetwork PruningPruning as a Game: Equilibrium-Driven Sparsification of Neural Networks
Neural network pruning is widely used to reduce model size and computational cost. Yet, most existing methods treat sparsity as an externally imposed constraint, enforced through heuristic importance scores or training-t…
Network PruningNeural expressiveness for beyond importance model compression
Neural Network Pruning has been established as driving force in the exploration of memory and energy efficient solutions with high throughput both during training and at test time. In this paper, we introduce a novel cri…
Model CompressionObject DetectionNetwork Pruning