Pith. sign in

REVIEW 5 cited by

Pruning-as-Search: Efficient Neural Architecture Search via Channel Pruning and Structural Reparameterization

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2206.01198 v1 pith:ZTAM75AF submitted 2022-06-02 cs.CV

Yanyu Li , Pu Zhao , Geng Yuan , Xue Lin , Yanzhi Wang , Xin Chen This is my paper · ORCID
classification cs.CV
keywords searchpruningarchitectureautomaticallychannelefficientneuralpruning-as-search
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Neural architecture search (NAS) and network pruning are widely studied efficient AI techniques, but not yet perfect. NAS performs exhaustive candidate architecture search, incurring tremendous search cost. Though (structured) pruning can simply shrink model dimension, it remains unclear how to decide the per-layer sparsity automatically and optimally. In this work, we revisit the problem of layer-width optimization and propose Pruning-as-Search (PaS), an end-to-end channel pruning method to search out desired sub-network automatically and efficiently. Specifically, we add a depth-wise binary convolution to learn pruning policies directly through gradient descent. By combining the structural reparameterization and PaS, we successfully searched out a new family of VGG-like and lightweight networks, which enable the flexibility of arbitrary width with respect to each layer instead of each stage. Experimental results show that our proposed architecture outperforms prior arts by around $1.0\%$ top-1 accuracy under similar inference speed on ImageNet-1000 classification task. Furthermore, we demonstrate the effectiveness of our width search on complex tasks including instance segmentation and image translation. Code and models are released.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Pruning Increases Orderedness in Recurrent Computation

    cs.LG 2025-07 conditional novelty 5.0 of 10

    Magnitude-based pruning (Top-K) increases a measure of topological orderedness in fully connected, weight-tied recurrent layers, without a clear performance drop on two toy tasks.

  2. Numerical Pruning for Efficient Autoregressive Models

    cs.LG 2024-12 conditional novelty 5.0 of 10

    A Newton's method derived importance score plus a constrained least-squares compensation prunes LLaMA and LlamaGen models with reported gains over LLM-Pruner, SliceGPT, and FLAP.

  3. Designing Semi-Structured Pruning of Graph Convolutional Networks for Skeleton-based Recognition

    cs.CV 2024-12 conditional novelty 5.0 of 10

    A learned cascade of band-stop, weight-sharing, and gating steps produces semi-structured pruning masks for skeleton GCNs, reporting better accuracy-for-speedup trade-offs than pure structured or unstructured pruning.

  4. Learning Coarse-to-Fine Pruning of Graph Convolutional Networks for Skeleton-based Recognition

    cs.CV 2024-12 conditional novelty 4.0 of 10

    Coarse-to-fine pruning, defined as a product of channel, row, column, and entry-wise masks, improves the accuracy-speedup tradeoff of pruned GCNs on SBU and FPHA skeleton benchmarks.

  5. 7B Fully Open Source Moxin-LLM/VLM -- From Pretraining to GRPO-based Reinforcement Learning Enhancement

    cs.CL 2024-12 conditional novelty 4.0 of 10

    The authors trained and openly released a 7B LLM, an instruction-tuned variant, a GRPO-based reasoning variant, and a VLM, claiming competitive or superior performance on zero-shot, few-shot, CoT, and VLM benchmarks.

Pith tools