Interference and Retention in Continual Learning

• URL: http://arxiv.org/abs/2607.09202v1
• Date: Fri, 10 Jul 2026 08:48:23 GMT
• Title: Interference and Retention in Continual Learning
• Abstract summary: We show that forgetting from learning a new task is exactly the interference energy induced on the old task.<n>IGFA is a replay-free, Fisher-free method that shares directions when tasks align and protects them when they conflict.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Continual learning commonly relies on post-hoc mechanisms such as replay, elastic regularization, or distillation. This work argues that forgetting should instead be modeled directly as interference between tasks. In the frozen-feature regime, forgetting from learning a new task is exactly the interference energy induced on the old task. In deep networks, the same quantity is recovered through path-averaged curvature with minimal additional forward passes. When task supports are disjoint, forgetting can be eliminated structurally and when task supports overlap in conflicting directions, a non-zero distortion floor is unavoidable. The same geometry optimally merges models through task-aware orthogonalization. From this analysis we derive Interference-Gated Functional Allocation (IGFA), a replay-free, Fisher-free method that shares directions when tasks align and protects them when they conflict. Across benchmarks, IGFA achieves lossless retention when tasks are structurally separable and moves unavoidable cost from irreversible forgetting into deferred but recoverable plasticity when they are not. It matches the strongest replay-free structural baselines on dissimilar-task streams and improves on unconditional projection when similarity makes transfer worth preserving.

Related papers

• ScrambleToolBench: Agents Search Exhaustively Even When Their Own Map Points to the Next Step [74.83535434786145]
  We introduce ScrambleToolBench, an interactive terminal benchmark designed to isolate behavioral reasoning.<n>The benchmark requires agents to uncover hidden tool behaviors entirely through trial-and-error interaction.<n>Our evaluation of state-of-the-art language models reveals that successful initial discovery does not translate into robust adaptation.
  arXiv  Detail & Related papers  (2026-08-03T15:07:46Z)
• SPECTRA: Context-Conditioned Spectral Movement Primitives for Robot Skill Generalization [13.880300186965469]
  We propose a frequency-domain imitation learning framework that couples task-space skill generation with joint-space execution regulation.<n>Experiments evaluate task-band reconstruction, robustness to composite demonstration corruption, out-of-distribution cross-board generalization, joint-space dynamic admissibility, end-effector path preservation, and deployment on a Franka Panda robot.
  arXiv  Detail & Related papers  (2026-07-08T04:02:19Z)
• OrthoTryOn: Geometric Orthogonalization for Conflict-Free Unified Fashion Generation [43.40052085990979]
  Unified fashion generation integrates tasks like virtual try-on and garment reconstruction into a single model to reduce task-specific adaptation costs.<n>We propose OrthoTryOn, a unified framework mitigating this interference within a shared Low- AdaptationRank (LoRA) module.
  arXiv  Detail & Related papers  (2026-06-26T09:23:25Z)
• Task-Restricted Symmetries in Recurrent Weight Space [0.0]
  Recurrent networks can contain substantial functional redundancy in weight space.<n>We study this redundancy in one-layer tanh RNNs using ordered real Schur coordinates.
  arXiv  Detail & Related papers  (2026-06-16T20:04:07Z)
• Sequential Learning and Catastrophic Forgetting in Differentiable Resistor Networks [0.0]
  We investigate sequential learning in differentiable resistor networks governed by Kirchhoff's laws.<n>We show that forgetting is controlled by task conflict and by the degree of adaptation to the new task.<n>These results position differentiable resistor networks as compact, physically interpretable testbeds for studying continual learning in tunable matter.
  arXiv  Detail & Related papers  (2026-05-02T11:15:57Z)
• Task Switching Without Forgetting via Proximal Decoupling [43.88767637201092]
  In continual learning, the primary challenge is to learn new information without forgetting old knowledge.<n>A common solution addresses this trade-off through regularization, penalizing changes to parameters critical for previous tasks.<n>We propose a different approach that separates task learning from stability enforcement via operator splitting.
  arXiv  Detail & Related papers  (2026-04-20T21:28:13Z)
• Referring-Aware Visuomotor Policy Learning for Closed-Loop Manipulation [91.20850436220267]
  We introduce the Referring-Aware Visuomotor Policy (ReV)<n>ReV incorporates sparse referring points provided by a human or a high-level reasoning planner.<n>It is trained only by applying targeted perturbations to expert demonstrations.
  arXiv  Detail & Related papers  (2026-04-07T07:41:11Z)
• TopoCurate:Modeling Interaction Topology for Tool-Use Agent Training [53.93696896939915]
  Training tool-use agents typically rely on Supervised Fine-Tuning (SFT) on successful trajectories and Reinforcement Learning (RL) on pass-rate-selected tasks.<n>We propose TopoCurate, an interaction-aware framework that projects multi-trial rollouts from the same task into a unified semantic quotient topology.<n>TopoCurate achieves consistent gains of 4.2% (SFT) and 6.9% (RL) over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-03-02T10:38:54Z)
• Geometric-Disentangelment Unlearning [106.99160454669902]
  gradient ascent on forget samples often harms retained knowledge.<n>We propose the Geometric-disment Unlearning (GU) that decomposes any candidate forget gradient update into tangential and normal components to retain space and executes only the normal component.<n>Our method is plug-and-play and can be attached to existing gradient-based unlearning procedures to mitigate side effects.
  arXiv  Detail & Related papers  (2025-11-21T09:58:25Z)
• Rotation Control Unlearning: Quantifying and Controlling Continuous Unlearning for LLM with The Cognitive Rotation Space [66.51378598755933]
  We propose a novel method, called Rotation Control Unlearning (RCU), to quantify and control the unlearning degree in the continuous unlearning process.<n>The skew symmetric loss is designed to construct the existence of the cognitive rotation space, where the changes of rotational angle can simulate the continuous unlearning process.<n> Experiments on multiple datasets confirm that our method without retained dataset achieves SOTA performance.
  arXiv  Detail & Related papers  (2025-09-30T03:59:29Z)
• REBAR: Retrieval-Based Reconstruction for Time-series Contrastive Learning [64.08293076551601]
  We propose a novel method of using a learned measure for identifying positive pairs. Our Retrieval-Based Reconstruction measure measures the similarity between two sequences. We show that the REBAR error is a predictor of mutual class membership.
  arXiv  Detail & Related papers  (2023-11-01T13:44:45Z)
• Compressing Deep ODE-Nets using Basis Function Expansions [105.05435207079759]
  We consider formulations of the weights as continuous-depth functions using linear combinations of basis functions. This perspective allows us to compress the weights through a change of basis, without retraining, while maintaining near state-of-the-art performance. In turn, both inference time and the memory footprint are reduced, enabling quick and rigorous adaptation between computational environments.
  arXiv  Detail & Related papers  (2021-06-21T03:04:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.