AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Where to Pay Attention in Sparse Training for Feature Selection?

Ghada Sokar, Zahra Atashgahi, Mykola Pechenizkiy, Decebal Constantin Mocanu

NeurIPS 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add loss-gradient sensitivity to neuron importance (ablation)WAST · Madelonaccuracy (%): 55.50 -> 83.27Improved
add loss-gradient sensitivity to neuron importance (ablation)WAST · PCMACaccuracy (%): 55.58 -> 60.51Improved
add loss-gradient sensitivity to neuron importance (ablation)WAST · HARaccuracy (%): 87.88 -> 91.20Improved
add loss-gradient sensitivity to neuron importance (ablation)WAST · SMKaccuracy (%): 84.21 -> 84.74No clear effect
add weight-magnitude term to neuron importance (ablation)WAST · SMKaccuracy (%): 75.26 -> 84.74Improved
add weight-magnitude term to neuron importance (ablation)WAST · HARaccuracy (%): 92.20 -> 91.20Hurt
add weight-magnitude term to neuron importance (ablation)WAST · PCMACaccuracy (%): 58.66 -> 60.51Mixed
add momentum (accumulated importance across iterations) (ablation)WAST · SMKaccuracy (%): 78.95 -> 84.74Improved
add momentum (accumulated importance across iterations) (ablation)WAST · USPSaccuracy (%): 96.60 -> 96.69No clear effect
include neuron importance in connection importance (ablation)WAST · PCMACaccuracy (%): 55.53 -> 60.51Improved
include neuron importance in connection importance (ablation)WAST · Madelonaccuracy (%): 83.27 -> 83.27No clear effect
replace random regrowth (QS) with attention-guided regrowth, 10 vs 100 epochsWAST · Madelonaccuracy (%): 82.07 -> 83.27Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy