Aug 2026· Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2· pp. 1554-1565· 0 citations· 8 references
Abstract
Existing Online Continual Learning (OCL) methods, particularly those based on Parameter-Efficient Fine-Tuning (PEFT), predominantly operate under a Static Inference Assumption, which means freezing model parameters immediately after training. This paradigm ignores the inevitable covariate shift in non-stationary test streams, resulting in suboptimal decision boundaries that fail to adapt to the immediate testing context. Furthermore, despite the computational efficiency of current analytic learning approaches, their reliance on Gaussian Random Projection introduces severe geometric distortion and feature aliasing in finite dimensions. Drawing inspiration from the Learning to Memorize at Test Time mechanism and the Pattern Separation process in the hippocampus, we propose Test-Time Memory Calibration (TTMC), a novel gradient-free analytic framework. Unlike traditional approaches that treat memory as a static statistic, TTMC views it as a dynamic associative pool. Specifically, we introduce a transductive calibration mechanism that seamlessly fuses the second-order statistics of the unlabelled test stream into the accumulated long-term memory via a closed-form solution, allowing for real-time alignment with the test distribution. To ensure the geometric stability of this dynamic test-time calibration, we theoretically prove the necessity of substituting random projections with Isometric Orthogonal Projections, which guarantee energy conservation and minimize feature interference. Our empirical evaluation demonstrates that TTMC consistently establishes a new state-of-the-art across diverse benchmarks. Notably, these performance gains are realized with zero backward passes and negligible computational overhead, underscoring the superior efficiency and structural robustness of our dynamic analytic framework. Code is available at https://github.com/hanyuyang99/TTMC.git.
Persistent intelligent systems require the ability to learn continually, but current machine learning approaches face significant challenges in this area compared to biological learning systems. Machine learning algorithms typically trade off retention of previously learned information and adaptation to new or changing data patterns. When continual learning capabilities are absent, algorithms must undergo retraining using the entire data set, an approach that becomes impractical when original training data are unavailable due to storage constraints, financial or computational costs, or privacy restrictions. However, biological animals can learn continually, without experiencing catastrophic forgetting. This paper attempts to build a high-level framework for how animals learn and preserve knowledge by modelling neural components and states that are known to be related to memory consolidation. We focus on three concepts: experience replay, REM sleep, and bilaterality. We propose 4MAS (4 Module Awake/Sleep), a novel macroarchitecture demonstrating how machine learning models might benefit from asymmetric hemispheres, each with their own long- and short-term memory mechanisms, and how a period of sleep between incremental learning tasks might benefit memory consolidation. Finally, we present results showing that our architecture achieves competitive results on the Split-MNIST, Split-Fashion-MNIST and Split-CIFAR-100 datasets, with 98.3%, 84.9%, and 29.29% accuracy respectively.
Benjamin Smith, Levin Kuhlmann, Kaushik Roy et al.· 0 citations
The results support DRMCL as a stability-oriented computational framework; they do not establish a circuit-level model of hippocampo-cortical consolidation or a new EEG decoding benchmark.
Together, these results link representational drift to the stability--plasticity trade-off: its magnitude is shaped by the mechanism that protects old knowledge, and suppressing it can restrict future learning.
The brain uses discrete spikes for dynamic computation, yet, how neural microcircuits (NMCs) solve temporal credit assignment using local spike timing remains a fundamental open question. Dominant spiking neural network (SNN) approaches circumvent this by approximating backpropagation through surrogate gradients, decoupling learning from biological spike timing. Here, we reformulate temporal credit assignment as a state separation problem: extracting task-required components induced by historical perturbations directly from the current neural state. This enables an online feedback learning framework for NMCs through a gradient tunneling (GT) algorithm and the lead-lag expansion technique that derives credit assignment from local synaptic spike timing, while remaining compatible with ANN-SNN hybrid architectures. Experimentally, GT-trained NMCs excel at long-timescale evidence integration and noise-robust memory retention, and perform comparably to leading SNN online learning methods on real-world benchmarks with far fewer parameters. The proposed framework addresses the two-decade-old NMC feedback learning problem and suggests a computationally plausible explanation for the brain's learning mechanisms.
Xiangnan Zhang, Jingxin Liu, Ranqi Lu et al.· 0 citations
The results suggest that the combination of sparse representations, local learning, and persistent memory is a promising direction for continual learning, while motivating further investigation into the respective roles of learning rules, representations, and architectural design in mitigating catastrophic forgetting.
