Escaping Stability-Plasticity Dilemma in Online Continual Learning for Motion Forecasting via Synergetic Memory Rehearsal

• URL: http://arxiv.org/abs/2508.19571v1
• Date: Wed, 27 Aug 2025 05:04:33 GMT
• Title: Escaping Stability-Plasticity Dilemma in Online Continual Learning for Motion Forecasting via Synergetic Memory Rehearsal
• Authors: Yunlong Lin, Chao Lu, Tongshuai Wu, Xiaocong Zhao, Guodong Du, Yanwei Sun, Zirui Li, Jianwei Gong,
• Abstract summary: We propose synergetic memory rehearsal (SyReM) for DNN-based motion forecasting.<n>SyReM maintains a compact memory buffer to represent learned knowledge.<n>It employs an inequality constraint that limits in the average loss over the memory buffer.<n>SyReM significantly mitigates catastrophic forgetting in past scenarios while improving forecasting accuracy in new ones.
• Score: 19.181540661354312
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep neural networks (DNN) have achieved remarkable success in motion forecasting. However, most DNN-based methods suffer from catastrophic forgetting and fail to maintain their performance in previously learned scenarios after adapting to new data. Recent continual learning (CL) studies aim to mitigate this phenomenon by enhancing memory stability of DNN, i.e., the ability to retain learned knowledge. Yet, excessive emphasis on the memory stability often impairs learning plasticity, i.e., the capacity of DNN to acquire new information effectively. To address such stability-plasticity dilemma, this study proposes a novel CL method, synergetic memory rehearsal (SyReM), for DNN-based motion forecasting. SyReM maintains a compact memory buffer to represent learned knowledge. To ensure memory stability, it employs an inequality constraint that limits increments in the average loss over the memory buffer. Synergistically, a selective memory rehearsal mechanism is designed to enhance learning plasticity by selecting samples from the memory buffer that are most similar to recently observed data. This selection is based on an online-measured cosine similarity of loss gradients, ensuring targeted memory rehearsal. Since replayed samples originate from learned scenarios, this memory rehearsal mechanism avoids compromising memory stability. We validate SyReM under an online CL paradigm where training samples from diverse scenarios arrive as a one-pass stream. Experiments on 11 naturalistic driving datasets from INTERACTION demonstrate that, compared to non-CL and CL baselines, SyReM significantly mitigates catastrophic forgetting in past scenarios while improving forecasting accuracy in new ones. The implementation is publicly available at https://github.com/BIT-Jack/SyReM.

Related papers

• TS-Memory: Plug-and-Play Memory for Time Series Foundation Models [63.21390142212087]
  Time Series Foundation Models (TSFMs) achieve strong zero-shot forecasting through large-scale pre-training.<n>Existing solutions face a trade-off: Parametric Adaptation can cause catastrophic forgetting, while Non-Parametric Retrieval improves forecasts but incurs high latency due to datastore search.<n>We propose Parametric Memory Distillation and implement it as TS-Memory, a lightweight memory adapter that augments frozen TSFMs.
  arXiv  Detail & Related papers  (2026-02-12T04:16:19Z)
• Holistic Continual Learning under Concept Drift with Adaptive Memory Realignment [6.0897744845912865]
  We introduce a holistic framework for continual learning under concept drift.<n>We propose Adaptive Memory Realignment (AMR), a lightweight alternative that equips rehearsal-based learners with a drift-aware adaptation mechanism.<n>AMR consistently counters concept drift, maintaining high accuracy with minimal overhead.
  arXiv  Detail & Related papers  (2025-07-03T04:41:20Z)
• Forget Forgetting: Continual Learning in a World of Abundant Memory [55.64184779530581]
  Continual learning has traditionally focused on minimizing exemplar memory.<n>This paper challenges this paradigm by investigating a more realistic regime.<n>We find that the core challenge shifts from stability to plasticity, as models become biased toward prior tasks and struggle to learn new ones.
  arXiv  Detail & Related papers  (2025-02-11T05:40:52Z)
• Exploring Learnability in Memory-Augmented Recurrent Neural Networks: Precision, Stability, and Empirical Insights [2.1485350418225244]
  This study explores the learnability of memory-less and memory-augmented RNNs, which are theoretically equivalent to Pushdown Automata. Experiments on fully trained and component-frozen models reveal that freezing the memory component significantly improves performance.
  arXiv  Detail & Related papers  (2024-10-04T05:29:51Z)
• How to Leverage Predictive Uncertainty Estimates for Reducing Catastrophic Forgetting in Online Continual Learning [12.33899500566626]
  This work presents an in-depth analysis of different uncertainty estimates and strategies for populating the memory.<n>We propose an alternative method for estimating predictive uncertainty via the generalised variance induced by the negative log-likelihood.<n>We demonstrate that the use of predictive uncertainty measures helps in reducing CF in different settings.
  arXiv  Detail & Related papers  (2024-07-10T13:51:15Z)
• Adversarially Diversified Rehearsal Memory (ADRM): Mitigating Memory Overfitting Challenge in Continual Learning [0.0]
  Continual learning focuses on learning non-stationary data distribution without forgetting previous knowledge. Rehearsal-based approaches are commonly used to combat catastrophic forgetting. We introduce the Adversarially Diversified Rehearsal Memory to address the memory overfitting challenge.
  arXiv  Detail & Related papers  (2024-05-20T06:56:43Z)
• Towards Continual Learning Desiderata via HSIC-Bottleneck Orthogonalization and Equiangular Embedding [55.107555305760954]
  We propose a conceptually simple yet effective method that attributes forgetting to layer-wise parameter overwriting and the resulting decision boundary distortion. Our method achieves competitive accuracy performance, even with absolute superiority of zero exemplar buffer and 1.02x the base model.
  arXiv  Detail & Related papers  (2024-01-17T09:01:29Z)
• Selective Memory Recursive Least Squares: Recast Forgetting into Memory in RBF Neural Network Based Real-Time Learning [2.31120983784623]
  In radial basis function neural network (RBFNN) based real-time learning tasks, forgetting mechanisms are widely used. This paper proposes a real-time training method named selective memory recursive least squares (SMRLS) in which the classical forgetting mechanisms are recast into a memory mechanism. With SMRLS, the input space of the RBFNN is evenly divided into a finite number of partitions and a synthesized objective function is developed using synthesized samples from each partition.
  arXiv  Detail & Related papers  (2022-11-15T05:29:58Z)
• A Memory Transformer Network for Incremental Learning [64.0410375349852]
  We study class-incremental learning, a training setup in which new classes of data are observed over time for the model to learn from. Despite the straightforward problem formulation, the naive application of classification models to class-incremental learning results in the "catastrophic forgetting" of previously seen classes. One of the most successful existing methods has been the use of a memory of exemplars, which overcomes the issue of catastrophic forgetting by saving a subset of past data into a memory bank and utilizing it to prevent forgetting when training future tasks.
  arXiv  Detail & Related papers  (2022-10-10T08:27:28Z)
• Learning Bayesian Sparse Networks with Full Experience Replay for Continual Learning [54.7584721943286]
  Continual Learning (CL) methods aim to enable machine learning models to learn new tasks without catastrophic forgetting of those that have been previously mastered. Existing CL approaches often keep a buffer of previously-seen samples, perform knowledge distillation, or use regularization techniques towards this goal. We propose to only activate and select sparse neurons for learning current and past tasks at any stage.
  arXiv  Detail & Related papers  (2022-02-21T13:25:03Z)
• Memory Replay with Data Compression for Continual Learning [80.95444077825852]
  We propose memory replay with data compression to reduce the storage cost of old training samples. We extensively validate this across several benchmarks of class-incremental learning and in a realistic scenario of object detection for autonomous driving.
  arXiv  Detail & Related papers  (2022-02-14T10:26:23Z)
• Reducing Catastrophic Forgetting in Self Organizing Maps with Internally-Induced Generative Replay [67.50637511633212]
  A lifelong learning agent is able to continually learn from potentially infinite streams of pattern sensory data. One major historic difficulty in building agents that adapt is that neural systems struggle to retain previously-acquired knowledge when learning from new samples. This problem is known as catastrophic forgetting (interference) and remains an unsolved problem in the domain of machine learning to this day.
  arXiv  Detail & Related papers  (2021-12-09T07:11:14Z)
• Online Limited Memory Neural-Linear Bandits with Likelihood Matching [53.18698496031658]
  We study neural-linear bandits for solving problems where both exploration and representation learning play an important role. We propose a likelihood matching algorithm that is resilient to catastrophic forgetting and is completely online.
  arXiv  Detail & Related papers  (2021-02-07T14:19:07Z)

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.