AI Paper Atlas

Research map / Continual learning / Online and replay-based

Supermasks in Superposition

Mitchell Wortsman, Vivek Ramanujan, Rosanne Liu, Aniruddha Kembhavi, Mohammad Rastegari, Jason Yosinski, Ali Farhadi

NeurIPS 2020 · Continual learning › Online and replay-based · approach: Gradient projection and plasticity preservation · 7 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
Initialize each new mask from the running mean of previous task masks (ablation)SupSup on SplitCIFAR100 · SplitCIFAR100Avg Acc@1: 89.57~\pm 0.64 -> \textbf{91.66} $~\pm 0.74$Improved
Use a running mean initialization for subsequent task masks (ablation)SupSup on SplitCIFAR · SplitCIFAR100training iterations for comparable accuracyImproved
Use output size s=200 rather than s=100 (ablation)SupSup with LeNet 300-100 · PermutedMNIST (250 tasks, Avg)accuracy: 93.66 -> 93.47No clear effect
Use output size s=25 rather than s=100 (ablation)SupSup with LeNet 300-100 · PermutedMNIST (250 tasks, Avg)accuracy: 93.66 -> 93.27Hurt
Use output size s=200 rather than s=100 (ablation)SupSup with FC 1024-1024 · PermutedMNIST (250 tasks, Avg)accuracy: 95.50 -> 96.07Improved
Use output size s=25 rather than s=100 (ablation)SupSup with FC 1024-1024 · PermutedMNIST (250 tasks, Avg)accuracy: 94.04 -> 65.34Hurt
Use the G objective instead of entropy H for task inference (ablation)SupSup with LeNet 300-100 · PermutedMNIST (250 tasks, Avg)accuracy: 93.66 -> 93.66No clear effect
Use the G objective instead of entropy H for task inference (ablation)SupSup with FC 1024-1024 · PermutedMNIST (250 tasks, Avg)accuracy: 95.98 -> 96.07Improved
Use one-shot rather than binary task inference (ablation)SupSup · RotatedMNISTaccuracyHurt
Infer task identity without any task identity during training or inference (ablation)SupSup · PermutedMNIST (2500 tasks)accuracy: 93.45 -> 92.54Hurt
Use entropy H rather than the confidence alternative M for ABatchE inference (ablation)ABatchE · PermutedMNISTaccuracyImproved
Use a larger batch for ABatchE task inference (ablation)ABatchE · PermutedMNISTforgetting: 16 imagesImproved

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