CoMemNet is a Continual Memory Network designed for traffic prediction on evolving sensor networks. It combines an online branch that adapts to current data with an exponential‑moving‑average target branch for stable reference, and uses a Wasserstein‑based drift sampler to selectively update drift‑sensitive nodes. A lightweight temporal memory replay buffer stores compact states, allowing efficient adaptation without traversing all historical data. Experiments on PeMS datasets show that CoMemNet maintains stable accuracy and outperforms retraining baselines in both prediction performance and training time.
arXiv:2606. 15807v1 Announce Type: cross Abstract: Traffic state prediction is a fundamental task in intelligent transportation systems.
The paper introduces the Continuous Evolution Pool (CEP), a replay‑free framework for online time series forecasting that tackles recurring concept drift. CEP maintains a dynamic pool of specialized forecasters, using lightweight statistical genes to identify concepts, spawn new models when distribution shifts occur, and prune obsolete ones under memory limits. Experiments on real‑world datasets show CEP reduces forecasting error by up to 24% compared to state‑of‑the‑art baselines, especially in scenarios with pronounced recurring drift.
arXiv:2609.36559v1 Announce Type: cross Abstract: Extrapolative temporal knowledge graph reasoning (TKGR) predicts future facts from historical snapshots. Most existing methods train once on an early...
The paper introduces AIGS, a lightweight Adaptive Incremental Gating System designed for online representation learning in non‑stationary data streams. AIGS uses a Shock Ratio feedback signal to drive a Continuous Plasticity Controller, enabling smooth adaptation between learning plasticity and memory retention while keeping per‑step complexity linear in the feature dimension. Experiments on smart‑city traffic, meteorological, and industrial datasets show that AIGS improves early‑warning lead times, accelerates recovery after abrupt changes, and enhances anomaly recall in noisy environments.
arXiv:2608. 02845v1 Announce Type: new Abstract: Tabular model performance degrades when feature distributions change over time or the relationship between features and outcome variables change over time, known as data drift and concept drift, respectively.
arXiv:2608.30923v1 Announce Type: cross Abstract: Stream learning is commonly evaluated through predictive performance and adaptation to concept drift. However, sustained operation of a stream learne...
arXiv:2610.07834v1 Announce Type: new Abstract: Retrieval-augmented time-series forecasting uses the continuations of historical segments similar to the current context as references for a forecaster...
arXiv:2608. 19488v1 Announce Type: new Abstract: Production machine learning systems degrade under concept drift, yet practitioners have little principled guidance on when to retrain.
RiskTraf introduces a risk-extrapolated residual learning approach for multi-variate traffic flow prediction, leveraging raw flow, speed, and occupancy data from the new PEMSB-3V benchmark. The method freezes a trained spatio-temporal backbone and adds a lightweight residual head that learns from historical speed and occupancy to correct flow predictions across different traffic regimes. Experiments show consistent improvements over various backbones and outperform existing debiasing and distribution-shift adaptation techniques.
arXiv:2602. 06932v5 Announce Type: replace Abstract: Speculative decoding can significantly accelerate LLM serving, yet most deployments today disentangle speculator training from serving, treating speculator training as a standalone offline modeling problem.
arXiv:2609.05862v1 Announce Type: new Abstract: Learning on dynamic graphs is difficult when changes in the underlying network are only partially observed. Acquiring current graph information incurs...
arXiv:2608. 01252v1 Announce Type: new Abstract: Catastrophic forgetting is a major problem in task-incremental learning, where neural networks tend to overwrite previously learned knowledge when trained on new tasks.