From 584d5c396992d6e320646d078c0e36255029a42a Mon Sep 17 00:00:00 2001 From: Dachuan Shi Date: Wed, 26 Jul 2023 14:04:50 +0800 Subject: [PATCH] Add a full list of pruning papers at ICML 2023 (10 in total) --- README.md | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/README.md b/README.md index 3692f17..ce6e9cb 100644 --- a/README.md +++ b/README.md @@ -42,6 +42,16 @@ A survey of structured pruning can be found at this link: [arxiv](https://arxiv. ### 2023 | Title | Venue | Type | Code | |:-------------------------------------------------------------------------------------------------------------------------------- |:-----:|:-------:|:----:| +| [SparseGPT: Massive Language Models Can be Accurately Pruned in One-Shot](https://proceedings.mlr.press/v202/frantar23a.html) | ICML | `W` | [PyTorch(Author)](https://github.com/IST-DASLab/sparsegpt) | +| [Why Random Pruning Is All We Need to Start Sparse](https://proceedings.mlr.press/v202/gadhikar23a.html) | ICML | `W` | [PyTorch(Author)](https://github.com/RelationalML/sparse_to_sparse) | +| [Fast as CHITA: Neural Network Pruning with Combinatorial Optimization](https://proceedings.mlr.press/v202/benbaki23a.html) | ICML | `W` | [PyTorch(Author)](https://github.com/mazumder-lab/CHITA) | +| [A Three-regime Model of Network Pruning](https://proceedings.mlr.press/v202/zhou23p.html) | ICML | `W` | [PyTorch(Author)](https://github.com/YefanZhou/ThreeRegimePruning) | +| [Instant Soup: Cheap Pruning Ensembles in A Single Pass Can Draw Lottery Tickets from Large Models](https://proceedings.mlr.press/v202/jaiswal23b.html) | ICML | `W` | [PyTorch(Author)](https://github.com/VITA-Group/instant_soup) | +| [Pruning via Sparsity-indexed ODE: a Continuous Sparsity Viewpoint](https://proceedings.mlr.press/v202/mo23c/mo23c.pdf) | ICML | `W` | [PyTorch(Author)](https://github.com/mzf666/sparsity-indexed-ode) | +| [UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers](https://proceedings.mlr.press/v202/shi23e.html) | ICML | `F` | [PyTorch(Author)](https://github.com/sdc17/UPop) | +| [Gradient-Free Structured Pruning with Unlabeled Data](https://proceedings.mlr.press/v202/nova23a.html) | ICML | `F` | | +| [Reconstructive Neuron Pruning for Backdoor Defense](https://proceedings.mlr.press/v202/li23v.html) | ICML | `F` | [PyTorch(Author)](https://github.com/bboylyg/RNP) | +| [UPSCALE: Unconstrained Channel Pruning](https://proceedings.mlr.press/v202/wan23a.html) | ICML | `F` | [PyTorch(Author)](https://github.com/apple/ml-upscale) | | [Revisiting Pruning at Initialization Through the Lens of Ramanujan Graph](https://openreview.net/forum?id=uVcDssQff_) | ICLR | `W` | [PyTorch(Author)](https://github.com/VITA-Group/ramanujan-on-pai)(Releasing) | | [Unmasking the Lottery Ticket Hypothesis: What's Encoded in a Winning Ticket's Mask?](https://openreview.net/forum?id=xSsW2Am-ukZ) | ICLR | `W` | - | | [Bit-Pruning: A Sparse Multiplication-Less Dot-Product](https://openreview.net/forum?id=YUDiZcZTI8) | ICLR | `W` | [Code Deleted](https://github.com/DensoITLab/bitprune) |