MANGO: Meta-Adaptive Network Gradient Optimization for Online Continual Learning

• URL: http://arxiv.org/abs/2605.19080v1
• Date: Mon, 18 May 2026 20:11:26 GMT
• Title: MANGO: Meta-Adaptive Network Gradient Optimization for Online Continual Learning
• Abstract summary: In Online Continual Learning (OCL), a neural network sequentially learns from a non-stationary data stream in a single-pass with access only to a limited memory replay buffer.<n>Existing methods counter forgetting via replay-based rehearsal, output level distillation, fixed regularization, or meta-learning on the current data.<n>We propose Meta-Adaptive Network Gradient Optimization (MANGO), an OCL framework that balances stability-plasticity via gradient-gating and meta-learned regularization.
• Score: 6.996743265827468
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In Online Continual Learning (OCL), a neural network sequentially learns from a non-stationary data stream in a single-pass with access only to a limited memory replay buffer. This contrasts sharply with off-line continual learning where training is multiple epoch dependent on large datasets. The main challenge faced by OCL is to overcome catastrophic forgetting of past tasks (stability) while learning new ones efficiently (plasticity). Existing methods counter forgetting via replay-based rehearsal, output level distillation, fixed regularization, or meta-learning on the current data. However, these methods have limitations: rehearsal introduces a stored sample bias; distillation operates on output-distributions without modulating parameter updates; fixed-regularization penalizes parameters irrespective of sensitivity; stream-only meta-learning lacks a feedback controlled parameter update. We propose Meta-Adaptive Network Gradient Optimization (MANGO), an OCL framework that balances stability-plasticity via gradient-gating and meta-learned regularization. Gradient-gating scales parameter updates based on sensitivity, preventing destructive updates. Meta-learned regularization adapts stability coefficients, evaluating the effect of parameter update on replay. In MANGO, replay acts as both a training signal and a forgetting evaluator. We evaluated our method on three standard OCL benchmark datasets. MANGO outperforms strong baselines, achieving state-of-the-art results with consistent performance across replay sizes. In domain incremental learning on CLEAR-10 and class incremental learning on CIFAR-100 and Tiny-ImageNet, it achieves highest accuracy among all baselines and achieves positive Backward Transfer, overcoming forgetting on CLEAR-10.

Related papers

• Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training [50.86545293331458]
  Reinforcement learning is structurally harder than supervised learning because the policy changes the data distribution it learns from.<n>We present a simple yet effective batch-adaptive objective that replaces fixed clipping with the normalized effective sample size of the policy ratios.
  arXiv  Detail & Related papers  (2026-05-12T16:44:47Z)
• Towards Realistic Class-Incremental Learning with Free-Flow Increments [17.558920457942936]
  We propose a model-agnostic framework for robust CIL learning under free-flow arrivals.<n>It comprises a class-wise mean (CWM) objective that replaces sample frequency weighted loss with uniformly aggregated class-conditional supervision.<n>Experiments confirm a clear performance degradation across various CIL baselines under FFCIL.
  arXiv  Detail & Related papers  (2026-04-03T06:19:58Z)
• GradAlign: Gradient-Aligned Data Selection for LLM Reinforcement Learning [55.03441672267886]
  We propose GradAlign, a gradient-aligned data selection method for reinforcement learning.<n>We evaluate GradAlign across three data regimes: unreliable reward signals, distribution imbalance, and low-utility training corpus.
  arXiv  Detail & Related papers  (2026-02-25T01:54:50Z)
• Online Continual Learning for Time Series: a Natural Score-driven Approach [2.8989185098518626]
  Online continual learning (OCL) methods adapt to changing environments without forgetting past knowledge.<n>Online time series forecasting (OTSF) is a real-world problem where data evolve in time and success depends on both rapid adaptation and long-term memory.<n>This paper aims to strengthen the theoretical and practical connections between time series methods and OCL.
  arXiv  Detail & Related papers  (2026-01-19T10:31:01Z)
• Beyond Freezing: Sparse Tuning Enhances Plasticity in Continual Learning with Pre-Trained Models [10.904981532789824]
  Continual Learning with Pre-trained Models holds great promise for efficient adaptation across sequential tasks.<n>Existing approaches freeze PTMs and rely on auxiliary modules like prompts or adapters.<n>We propose Mutual Information-guided Sparse Tuning (MIST), a plug-and-play method that selectively updates a small subset of PTM parameters.
  arXiv  Detail & Related papers  (2025-05-26T13:09:25Z)
• Online Curvature-Aware Replay: Leveraging $\mathbf{2^{nd}}$ Order Information for Online Continual Learning [2.0165668334347187]
  We formalize replay-based online joint optimization with explicit KL-divergence constraints on replay data.<n>We show how to adapt the estimation of the FIM to a continual setting second-order optimization for non-iid data.<n>OCAR outperforms state-of-the-art methods in continual metrics achieving higher average accuracy throughout the training process in three different benchmarks.
  arXiv  Detail & Related papers  (2025-02-03T22:31:36Z)
• ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts [71.91042186338163]
  ALoRE is a novel PETL method that reuses the hypercomplex parameterized space constructed by Kronecker product to Aggregate Low Rank Experts.<n>Thanks to the artful design, ALoRE maintains negligible extra parameters and can be effortlessly merged into the frozen backbone.
  arXiv  Detail & Related papers  (2024-12-11T12:31:30Z)
• Large Continual Instruction Assistant [59.585544987096974]
  Continual Instruction Tuning (CIT) is adopted to instruct Large Models to follow human intent data by data.<n>Existing update gradient would heavily destroy the performance on previous datasets during CIT process.<n>We propose a general continual instruction tuning framework to address the challenge.
  arXiv  Detail & Related papers  (2024-10-08T11:24:59Z)
• Rapid Adaptation in Online Continual Learning: Are We Evaluating It Right? [135.71855998537347]
  We revisit the common practice of evaluating adaptation of Online Continual Learning (OCL) algorithms through the metric of online accuracy. We show that this metric is unreliable, as even vacuous blind classifiers can achieve unrealistically high online accuracy. Existing OCL algorithms can also achieve high online accuracy, but perform poorly in retaining useful information.
  arXiv  Detail & Related papers  (2023-05-16T08:29:33Z)
• Improving Representational Continuity via Continued Pretraining [76.29171039601948]
  Transfer learning community (LP-FT) outperforms naive training and other continual learning methods. LP-FT also reduces forgetting in a real world satellite remote sensing dataset (FMoW) variant of LP-FT gets state-of-the-art accuracies on an NLP continual learning benchmark.
  arXiv  Detail & Related papers  (2023-02-26T10:39:38Z)

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.