gradient-projection

Tag

Cards List
#gradient-projection

Interference and Retention in Continual Learning

arXiv cs.LG · 2026-07-13 Cached

This paper proposes modeling forgetting in continual learning as interference between tasks and introduces Interference-Gated Functional Allocation (IGFA), a replay-free, Fisher-free method that shares or protects directions based on task geometry, achieving lossless retention when tasks are separable.

0 favorites 0 likes
#gradient-projection

MAAT: Multi-phase Adapter-Aware Targeted Unlearning

arXiv cs.LG · 2026-06-01 Cached

The paper identifies a blind spot in machine unlearning benchmarks: underrepresentation of causal (Why-type) knowledge, and proposes 5WBench, a balanced benchmark, and Maat, a three-phase unlearning framework on LoRA adapters that achieves high forgetting and retention on causal facts.

0 favorites 0 likes
#gradient-projection

Metric-Gradient Projection for Stable Multi-Agent Policy Learning

arXiv cs.LG · 2026-05-20

Introduces HPML, a method that projects the joint update field of multi-agent systems onto a metric-gradient component to stabilize and improve multi-agent reinforcement learning. It provides theoretical guarantees and shows improved stability and returns on CTDE benchmarks.

0 favorites 0 likes
#gradient-projection

Interference-Aware Multi-Task Unlearning

arXiv cs.AI · 2026-05-20 Cached

This paper introduces an interference-aware framework for multi-task machine unlearning, addressing task-level and instance-level interference through task-aware gradient projection and instance-level gradient orthogonalization, achieving effective unlearning on multi-task computer vision benchmarks.

0 favorites 0 likes
← Back to home

Submit Feedback