AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Exploring Nonlinear Pathway in Parameter Space for Machine Unlearning

Yingdan Shi, Ren Wang

ICML 2026 · Architectures and efficiency › Pruning and efficient tuning · approach: Low-rank compression and merging · 0 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 MCUβ pathway search on top of NegGrad+NegGrad+ · CIFAR-10 10% random forgetting (PreResNet-110)Avg. Gap: 2.97 -> 1.00Improved
add MCUβ on top of FTFT · CIFAR-10 10% random forgettingAvg. Gap: 6.57 -> 3.37Improved
add MCUβ on top of GAGA · CIFAR-10 10% random forgettingAvg. Gap: 7.31 -> 3.45Improved
add MCUβ on top of RLRL · CIFAR-10 10% random forgettingAvg. Gap: 2.70 -> 1.46Improved
add MCUβ on top of SalUnSalUn · CIFAR-10 10% random forgettingAvg. Gap: 5.99 -> 3.68Improved
adaptive beta instead of fixed beta (ablation)MCU · CIFAR-10 10% random forgettingAvg. Gap: 1.18 -> 1.00Improved
Bezier curve instead of Polychain pathway (ablation)MCUβ · CIFAR-10 10% random forgettingAvg. Gap: 1.28 -> 1.00 (Polychain-3 vs Bezier)Improved
more Polychain control points (ablation)MCUβ Polychain · CIFAR-10 10% random forgettingAvg. Gap: 1.03 (c=1), 1.53 (c=2), 1.28 (c=3)No clear effect
linear interpolation between original and pre-unlearning model instead of Bezier (ablation)MCU · CIFAR-10 10% random forgettingaccuracy gapHurt
entire-parameter mask (10%) instead of no mask (ablation)MCU · CIFAR-10 10% random forgettingepoch time: 75.23% speedupImproved
parameter mask instead of random 10% mask (ablation)MCU · CIFAR-10 10% random forgettingDr accuracy drop at t=0.5: 3.44% drop with random maskImproved
increase beta (ablation)MCU · CIFAR-10 10% random forgettingavg accuracy gap / effective region: gap 1.20 (0.1) -> 0.66 (0.3)Mixed

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