Temporal-Difference Variational Continual Learning

• URL: http://arxiv.org/abs/2410.07812v2
• Date: Wed, 14 May 2025 18:18:45 GMT
• Title: Temporal-Difference Variational Continual Learning
• Authors: Luckeciano C. Melo, Alessandro Abate, Yarin Gal,
• Abstract summary: We propose new learning objectives that integrate the regularization effects of multiple previous posterior estimations.<n>Our approach effectively mitigates Catastrophic Forgetting, outperforming strong Variational CL methods.
• Score: 89.32940051152782
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Machine Learning models in real-world applications must continuously learn new tasks to adapt to shifts in the data-generating distribution. Yet, for Continual Learning (CL), models often struggle to balance learning new tasks (plasticity) with retaining previous knowledge (memory stability). Consequently, they are susceptible to Catastrophic Forgetting, which degrades performance and undermines the reliability of deployed systems. In the Bayesian CL literature, variational methods tackle this challenge by employing a learning objective that recursively updates the posterior distribution while constraining it to stay close to its previous estimate. Nonetheless, we argue that these methods may be ineffective due to compounding approximation errors over successive recursions. To mitigate this, we propose new learning objectives that integrate the regularization effects of multiple previous posterior estimations, preventing individual errors from dominating future posterior updates and compounding over time. We reveal insightful connections between these objectives and Temporal-Difference methods, a popular learning mechanism in Reinforcement Learning and Neuroscience. Experiments on challenging CL benchmarks show that our approach effectively mitigates Catastrophic Forgetting, outperforming strong Variational CL methods.

Related papers

• Mind the Gap: Preserving and Compensating for the Modality Gap in CLIP-Based Continual Learning [11.50324946279326]
  Contrastive Language-Image Pre-trained model (CLIP) exhibiting strong capabilities across various downstream tasks.<n>We analyze the variations in the modality gap during the fine-tuning of vision-language pre-trained models.<n>We propose a simple yet effective method, MG-CLIP, that improves CLIP's performance in class-incremental learning.
  arXiv  Detail & Related papers  (2025-07-12T02:28:42Z)
• Continual Learning in Vision-Language Models via Aligned Model Merging [84.47520899851557]
  We present a new perspective based on model merging to maintain stability while still retaining plasticity.<n>To maximize the effectiveness of the merging process, we propose a simple mechanism that promotes learning aligned weights with previous ones.
  arXiv  Detail & Related papers  (2025-05-30T20:52:21Z)
• Train with Perturbation, Infer after Merging: A Two-Stage Framework for Continual Learning [59.6658995479243]
  We propose texttext-Perturb-and-Merge (P&M), a novel continual learning framework that integrates model merging into the CL paradigm to avoid forgetting.<n>Through theoretical analysis, we minimize the total loss increase across all tasks and derive an analytical solution for the optimal merging coefficient.<n>Our proposed approach achieves state-of-the-art performance on several continual learning benchmark datasets.
  arXiv  Detail & Related papers  (2025-05-28T14:14:19Z)
• STAR: Stability-Inducing Weight Perturbation for Continual Learning [4.623295991242981]
  A key challenge in continual learning is that as the model is updated to learn new tasks, it becomes susceptible to catastrophic forgetting. A popular approach to mitigate forgetting during continual learning is to maintain a small buffer of previously-seen samples and to replay them during training. We propose a novel loss function, STAR, that exploits the worst-case parameter perturbation that reduces the KL-divergence of model predictions.
  arXiv  Detail & Related papers  (2025-03-03T14:32:03Z)
• Spurious Forgetting in Continual Learning of Language Models [20.0936011355535]
  Recent advancements in large language models (LLMs) reveal a perplexing phenomenon in continual learning. Despite extensive training, models experience significant performance declines. This study proposes that such performance drops often reflect a decline in task alignment rather than true knowledge loss.
  arXiv  Detail & Related papers  (2025-01-23T08:09:54Z)
• Continual Task Learning through Adaptive Policy Self-Composition [54.95680427960524]
  CompoFormer is a structure-based continual transformer model that adaptively composes previous policies via a meta-policy network. Our experiments reveal that CompoFormer outperforms conventional continual learning (CL) methods, particularly in longer task sequences.
  arXiv  Detail & Related papers  (2024-11-18T08:20:21Z)
• ICL-TSVD: Bridging Theory and Practice in Continual Learning with Pre-trained Models [103.45785408116146]
  Continual learning (CL) aims to train a model that can solve multiple tasks presented sequentially. Recent CL approaches have achieved strong performance by leveraging large pre-trained models that generalize well to downstream tasks. However, such methods lack theoretical guarantees, making them prone to unexpected failures. We bridge this gap by integrating an empirically strong approach into a principled framework, designed to prevent forgetting.
  arXiv  Detail & Related papers  (2024-10-01T12:58:37Z)
• Continual Human Pose Estimation for Incremental Integration of Keypoints and Pose Variations [12.042768320132694]
  This paper reformulates cross-dataset human pose estimation as a continual learning task. We benchmark this formulation against established regularization-based methods for mitigating catastrophic forgetting. We show that our approach outperforms existing regularization-based continual learning strategies.
  arXiv  Detail & Related papers  (2024-09-30T16:29:30Z)
• Train-Attention: Meta-Learning Where to Focus in Continual Knowledge Learning [15.475427498268393]
  The Train-Attention-Augmented Language Model (TAALM) enhances learning efficiency by dynamically predicting and applying weights to tokens based on their usefulness. We show that TAALM proves the state-of-the-art performance upon the baselines, and also shows synergistic compatibility when integrated with previous CKL approaches.
  arXiv  Detail & Related papers  (2024-07-24T01:04:34Z)
• Towards Effective Evaluations and Comparisons for LLM Unlearning Methods [97.2995389188179]
  This paper seeks to refine the evaluation of machine unlearning for large language models. It addresses two key challenges -- the robustness of evaluation metrics and the trade-offs between competing goals.
  arXiv  Detail & Related papers  (2024-06-13T14:41:00Z)
• Towards Robust Continual Learning with Bayesian Adaptive Moment Regularization [51.34904967046097]
  Continual learning seeks to overcome the challenge of catastrophic forgetting, where a model forgets previously learnt information. We introduce a novel prior-based method that better constrains parameter growth, reducing catastrophic forgetting. Results show that BAdam achieves state-of-the-art performance for prior-based methods on challenging single-headed class-incremental experiments.
  arXiv  Detail & Related papers  (2023-09-15T17:10:51Z)
• Multimodal Parameter-Efficient Few-Shot Class Incremental Learning [1.9220716793379256]
  Few-Shot Class Incremental Learning (FSCIL) is a challenging continual learning task, where limited training examples are available during several learning sessions. To succeed in this task, it is necessary to avoid over-fitting new classes caused by biased distributions in the few-shot training sets. CPE-CLIP significantly improves FSCIL performance compared to state-of-the-art proposals while also drastically reducing the number of learnable parameters and training costs.
  arXiv  Detail & Related papers  (2023-03-08T17:34:15Z)
• Mitigating Forgetting in Online Continual Learning via Contrasting Semantically Distinct Augmentations [22.289830907729705]
  Online continual learning (OCL) aims to enable model learning from a non-stationary data stream to continuously acquire new knowledge as well as retain the learnt one. Main challenge comes from the "catastrophic forgetting" issue -- the inability to well remember the learnt knowledge while learning the new ones.
  arXiv  Detail & Related papers  (2022-11-10T05:29:43Z)
• Imitating, Fast and Slow: Robust learning from demonstrations via decision-time planning [96.72185761508668]
  Planning at Test-time (IMPLANT) is a new meta-algorithm for imitation learning. We demonstrate that IMPLANT significantly outperforms benchmark imitation learning approaches on standard control environments.
  arXiv  Detail & Related papers  (2022-04-07T17:16:52Z)
• Accurate and Robust Feature Importance Estimation under Distribution Shifts [49.58991359544005]
  PRoFILE is a novel feature importance estimation method. We show significant improvements over state-of-the-art approaches, both in terms of fidelity and robustness.
  arXiv  Detail & Related papers  (2020-09-30T05:29:01Z)

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.