Mitigating Catastrophic Forgetting in Streaming Generative and Predictive Learning via Stateful Replay

• URL: http://arxiv.org/abs/2511.17936v1
• Date: Sat, 22 Nov 2025 06:25:54 GMT
• Title: Mitigating Catastrophic Forgetting in Streaming Generative and Predictive Learning via Stateful Replay
• Authors: Wenzhang Du,
• Abstract summary: We present a unified study of stateful replay for streaming autoencoding time series forecasting, and classification.<n>We evaluate a single replay mechanism on six streaming scenarios built from Rotated MNIST, ElectricityLoadDiagrams 2011-2014, and Airlines delay data.<n>On heterogeneous multi task streams, replay reduces average forgetting by a factor of two to three, while on benign time based streams both methods perform similarly.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Many deployed learning systems must update models on streaming data under memory constraints. The default strategy, sequential fine-tuning on each new phase, is architecture-agnostic but often suffers catastrophic forgetting when later phases correspond to different sub-populations or tasks. Replay with a finite buffer is a simple alternative, yet its behaviour across generative and predictive objectives is not well understood. We present a unified study of stateful replay for streaming autoencoding, time series forecasting, and classification. We view both sequential fine-tuning and replay as stochastic gradient methods for an ideal joint objective, and use a gradient alignment analysis to show when mixing current and historical samples should reduce forgetting. We then evaluate a single replay mechanism on six streaming scenarios built from Rotated MNIST, ElectricityLoadDiagrams 2011-2014, and Airlines delay data, using matched training budgets and three seeds. On heterogeneous multi task streams, replay reduces average forgetting by a factor of two to three, while on benign time based streams both methods perform similarly. These results position stateful replay as a strong and simple baseline for continual learning in streaming environments.

Related papers

• Squeezing More from the Stream : Learning Representation Online for Streaming Reinforcement Learning [14.799267729619428]
  In streaming Reinforcement Learning (RL), transitions are observed and discarded immediately after a single update.<n>We propose extending Self-Predictive Representations (SPR) to the streaming pipeline to maximize the utility of every observed frame.<n>We show that our method learns significantly richer representations, bridging the performance gap caused by the absence of a replay buffer.
  arXiv  Detail & Related papers  (2026-02-10T04:06:32Z)
• FOREVER: Forgetting Curve-Inspired Memory Replay for Language Model Continual Learning [63.20028888397869]
  FOREVER (FORgEtting curVe-inspired mEmory) is a novel framework that aligns replay schedules with a model-centric notion of time.<n>Building on this approach, FOREVER incorporates a forgetting curve-based replay scheduler to determine when to replay and an intensity-aware regularization mechanism to adaptively control how to replay.
  arXiv  Detail & Related papers  (2026-01-07T13:55:14Z)
• End-to-End Training for Autoregressive Video Diffusion via Self-Resampling [63.84672807009907]
  Autoregressive video diffusion models hold promise for world simulation but are vulnerable to exposure bias arising from the train-test mismatch.<n>We introduce Resampling Forcing, a teacher-free framework that enables training autoregressive video models from scratch and at scale.
  arXiv  Detail & Related papers  (2025-12-17T18:53:29Z)
• Stable Video Infinity: Infinite-Length Video Generation with Error Recycling [76.91310169118408]
  We propose Stable Video Infinity (SVI) that is able to generate infinite-length videos with high temporal consistency, plausible scene transitions, and controllable streaming storylines.<n> SVI incorporates Error-Recycling Fine-Tuning, a new type of efficient training that recycles the Diffusion Transformer's self-generated errors into supervisory prompts.<n>We evaluate SVI on three benchmarks, including consistent, creative, and conditional settings, thoroughly verifying its versatility and state-of-the-art role.
  arXiv  Detail & Related papers  (2025-10-10T09:45:46Z)
• Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion [67.94300151774085]
  We introduce Self Forcing, a novel training paradigm for autoregressive video diffusion models.<n>It addresses the longstanding issue of exposure bias, where models trained on ground-truth context must generate sequences conditioned on their own imperfect outputs.
  arXiv  Detail & Related papers  (2025-06-09T17:59:55Z)
• Generative Regression Based Watch Time Prediction for Short-Video Recommendation [36.95095097454143]
  Watch time prediction has emerged as a pivotal task in short video recommendation systems.<n>Recent studies have attempted to address these issues by converting the continuous watch time estimation into an ordinal regression task.<n>We propose a novel Generative Regression (GR) framework that reformulates WTP as a sequence generation task.
  arXiv  Detail & Related papers  (2024-12-28T16:48:55Z)
• ODEStream: A Buffer-Free Online Learning Framework with ODE-based Adaptor for Streaming Time Series Forecasting [11.261457967759688]
  ODEStream is a buffer-free continual learning framework that incorporates a temporal isolation layer to capture temporal dependencies within the data.<n>It generates a continuous data representation, enabling seamless adaptation to changing dynamics in a data streaming scenario.<n>Our approach focuses on learning how the dynamics and distribution of historical data change over time, facilitating direct processing of streaming sequences.
  arXiv  Detail & Related papers  (2024-11-11T22:36:33Z)
• Watch Your Step: Optimal Retrieval for Continual Learning at Scale [1.7265013728931]
  In continual learning, a model learns incrementally over time while minimizing interference between old and new tasks. One of the most widely used approaches in continual learning is referred to as replay. We propose a framework for evaluating selective retrieval strategies, categorized by simple, independent class- and sample-selective primitives. We propose a set of strategies to prevent duplicate replays and explore whether new samples with low loss values can be learned without replay.
  arXiv  Detail & Related papers  (2024-04-16T17:35:35Z)
• Learning from One Continuous Video Stream [70.30084026960819]
  We introduce a framework for online learning from a single continuous video stream. This poses great challenges given the high correlation between consecutive video frames. We employ pixel-to-pixel modelling as a practical and flexible way to switch between pre-training and single-stream evaluation.
  arXiv  Detail & Related papers  (2023-12-01T14:03:30Z)
• PCR: Proxy-based Contrastive Replay for Online Class-Incremental Continual Learning [16.67238259139417]
  Existing replay-based methods effectively alleviate this issue by saving and replaying part of old data in a proxy-based or contrastive-based replay manner. We propose a novel replay-based method called proxy-based contrastive replay (PCR)
  arXiv  Detail & Related papers  (2023-04-10T06:35:19Z)
• Adaptive Cross Batch Normalization for Metric Learning [75.91093210956116]
  Metric learning is a fundamental problem in computer vision. We show that it is equally important to ensure that the accumulated embeddings are up to date. In particular, it is necessary to circumvent the representational drift between the accumulated embeddings and the feature embeddings at the current training iteration.
  arXiv  Detail & Related papers  (2023-03-30T03:22:52Z)

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.