CATA: Continual Machine Unlearning via Conflict-Averse Task Arithmetic

• URL: http://arxiv.org/abs/2605.18610v1
• Date: Mon, 18 May 2026 16:21:41 GMT
• Title: CATA: Continual Machine Unlearning via Conflict-Averse Task Arithmetic
• Abstract summary: Vision-language models (VLMs) have shown remarkable ability in aligning visual and textual representations, enabling a wide range of multimodal applications.<n>Large-scale training data inevitably raises concerns about privacy, copyright, and undesirable content, creating a strong need for machine unlearning.<n>We propose CATA, a conflict-averse task arithmetic method that represents each forget request as an unlearning task vector.
• Score: 14.598390101939001
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision-language models (VLMs) have shown remarkable ability in aligning visual and textual representations, enabling a wide range of multimodal applications. However, their large-scale training data inevitably raises concerns about privacy, copyright, and undesirable content, creating a strong need for machine unlearning. While existing studies mainly focus on single-shot unlearning, practical VLM deployment often involves sequential removal requests over time, giving rise to continual machine unlearning. In this work, we make the first attempt to study continual unlearning for VLMs and identify three key challenges in this setting: effectiveness in removing target knowledge, fidelity in preserving retained model utility, and persistence in preventing knowledge re-emergence under sequential updates. To address these challenges, we propose CATA, a conflict-averse task arithmetic method that represents each forget request as an unlearning task vector. By maintaining historical task vectors and performing sign-aware conflict-averse aggregation, CATA suppresses conflicting update components that may weaken previous forgetting effects. Extensive experiments under both single-shot and continual settings show that CATA outperforms baselines in terms of forgetting effectiveness, model fidelity, and forgetting persistence.

Related papers

• A Model Merging Approach for Continual MLLM Unlearning [22.83414107472909]
  Merging for Continual Unlearning (MCU) is an approach that dynamically merges multiple one-shot unlearning adapters into a unified adapter upon receiving each new unlearning request.<n>MCU achieves superior unlearning effectiveness while preserving both retained knowledge and general multimodal utility.
  arXiv  Detail & Related papers  (2026-08-05T07:37:23Z)
• Learn to Think: Improving Multimodal Reasoning through Vision-Aware Self-Improvement Training [82.17582358979884]
  Post-training with explicit reasoning traces is common to improve the reasoning capabilities of Multimodal Large Language Models (MLLMs)<n>We propose VISTA, a vision-aware self-improvement training framework for enhancing the multimodal reasoning of MLLMs.
  arXiv  Detail & Related papers  (2026-05-12T10:44:35Z)
• WeMMU: Enhanced Bridging of Vision-Language Models and Diffusion Models via Noisy Query Tokens [69.97021957331326]
  We propose Noisy Query Tokens, which learn a distributed representation space between the VLM and Diffusion Model via end-to-end optimization.<n>We also introduce a VAE branch with linear projection to recover fine-grained image details.
  arXiv  Detail & Related papers  (2025-12-02T09:02:20Z)
• Learning with Preserving for Continual Multitask Learning [4.847042727427382]
  We introduce Learning with Preserving (LwP), a novel framework that shifts the focus from preserving task outputs to maintaining the shared representation space.<n>LwP not only mitigates catastrophic forgetting but also consistently outperforms state-of-the-art baselines in CMTL tasks.
  arXiv  Detail & Related papers  (2025-11-11T22:23:20Z)
• Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgetting [70.83781268763215]
  Vision-language models (VLMs) have achieved impressive performance across diverse multimodal tasks by leveraging large-scale pre-training.<n>VLMs face unique challenges such as cross-modal feature drift, parameter interference due to shared architectures, and zero-shot capability erosion.<n>This survey aims to serve as a comprehensive and diagnostic reference for researchers developing lifelong vision-language systems.
  arXiv  Detail & Related papers  (2025-08-06T09:03:10Z)
• MoCa: Modality-aware Continual Pre-training Makes Better Bidirectional Multimodal Embeddings [75.0617088717528]
  MoCa is a framework for transforming pre-trained VLM backbones into effective bidirectional embedding models.<n>MoCa consistently improves performance across MMEB and ViDoRe-v2 benchmarks, achieving new state-of-the-art results.
  arXiv  Detail & Related papers  (2025-06-29T06:41:00Z)
• LLaVA-c: Continual Improved Visual Instruction Tuning [41.83222301318741]
  Multimodal models like LLaVA-1.5 achieve state-of-the-art visual understanding through visual instruction tuning on multitask datasets.<n>We show that task-by-task continual learning can achieve results that match or surpass multitask joint learning.
  arXiv  Detail & Related papers  (2025-06-10T10:27:52Z)
• CSTA: Spatial-Temporal Causal Adaptive Learning for Exemplar-Free Video Class-Incremental Learning [62.69917996026769]
  A class-incremental learning task requires learning and preserving both spatial appearance and temporal action involvement.<n>We propose a framework that equips separate adapters to learn new class patterns, accommodating the incremental information requirements unique to each class.<n>A causal compensation mechanism is proposed to reduce the conflicts during increment and memorization for between different types of information.
  arXiv  Detail & Related papers  (2025-01-13T11:34:55Z)
• SMoLoRA: Exploring and Defying Dual Catastrophic Forgetting in Continual Visual Instruction Tuning [16.873306091966693]
  Visual instruction tuning enables large language models (MLLMs) to handle a wide range of vision tasks by framing them as language-based instructions.<n>We identify a dual form of catastrophic forgetting in CVIT, where MLLMs forget previously learned visual understanding and also experience a decline in instruction following abilities.<n>We introduce the Separable Mixture of Low-Rank Adaptation (SMoLoRA) framework, which employs separable routing through two distinct modules-one for visual understanding and another for instruction following.
  arXiv  Detail & Related papers  (2024-11-21T09:00:15Z)
• Hierarchical Few-Shot Imitation with Skill Transition Models [66.81252581083199]
  Few-shot Imitation with Skill Transition Models (FIST) is an algorithm that extracts skills from offline data and utilizes them to generalize to unseen tasks. We show that FIST is capable of generalizing to new tasks and substantially outperforms prior baselines in navigation experiments.
  arXiv  Detail & Related papers  (2021-07-19T15:56:01Z)

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.