Learning to Query History: Nonstationary Classification via Learned Retrieval

• URL: http://arxiv.org/abs/2604.07027v1
• Date: Wed, 08 Apr 2026 12:45:50 GMT
• Title: Learning to Query History: Nonstationary Classification via Learned Retrieval
• Abstract summary: We introduce a learned discrete retrieval mechanism that samples relevant historical examples via input-dependent queries.<n>This enables the full corpus of historical data to remain on an arbitrary during training and deployment.
• Score: 6.402212089830528
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Nonstationarity is ubiquitous in practical classification settings, leading deployed models to perform poorly even when they generalize well to holdout sets available at training time. We address this by reframing nonstationary classification as time series prediction: rather than predicting from the current input alone, we condition the classifier on a sequence of historical labeled examples that extends beyond the training cutoff. To scale to large sequences, we introduce a learned discrete retrieval mechanism that samples relevant historical examples via input-dependent queries, trained end-to-end with the classifier using a score-based gradient estimator. This enables the full corpus of historical data to remain on an arbitrary filesystem during training and deployment. Experiments on synthetic benchmarks and Amazon Reviews '23 (electronics category) show improved robustness to distribution shift compared to standard classifiers, with VRAM scaling predictably as the length of the historical data sequence increases.

Related papers

• Combining Statistical Features and Deep Encodings for Rehearsal-Based Class-Incremental Time Series Classification [1.0195618602298682]
  We present a novel approach for performing class incremental continual learning for the classification of time series data.<n>The proposed system achieves competitive average accuracy across all datasets while maintaining low forgetting rates across all experimental configurations.
  arXiv  Detail & Related papers  (2026-06-02T08:02:42Z)
• Do Not Imitate, Reinforce: Iterative Classification via Belief Refinement [10.794100274863816]
  We propose Reinforced Iterative Classification (RIC), which replaces the imitative objective with Reinforcement Learning (RL)<n>RIC deploys a recurrent agent that iteratively updates a predictive distribution over classes, receiving reward for stepwise improvement in prediction quality.<n>On image classification benchmarks, RIC matches the accuracy of supervised baselines with improved calibration and learns to allocate computation adaptively across inputs.
  arXiv  Detail & Related papers  (2026-04-23T23:06:48Z)
• Rethinking Zero-Shot Time Series Classification: From Task-specific Classifiers to In-Context Inference [34.15455500037426]
  We propose TIC-FM, an in-context learning framework that treats the labeled training set as context and predicts labels for all test instances in a single forward pass.<n>TIC-FM pairs a time series encoder and a lightweight projection adapter with a split-masked latent memory Transformer.<n>Experiments on 128 UCR datasets show strong accuracy, with consistent gains in the extreme low-label situation.
  arXiv  Detail & Related papers  (2026-01-31T09:17:45Z)
• FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning [21.088762527081883]
  Exemplar-free class-incremental learning (CIL) poses several challenges since it prohibits the rehearsal of data from previous tasks. Recent approaches to incrementally learning the classifier by freezing the feature extractor after the first task have gained much attention. We explore prototypical networks for CIL, which generate new class prototypes using the frozen feature extractor and classify the features based on the Euclidean distance to the prototypes.
  arXiv  Detail & Related papers  (2023-09-25T11:54:33Z)
• Revisiting Long-tailed Image Classification: Survey and Benchmarks with New Evaluation Metrics [88.39382177059747]
  A corpus of metrics is designed for measuring the accuracy, robustness, and bounds of algorithms for learning with long-tailed distribution. Based on our benchmarks, we re-evaluate the performance of existing methods on CIFAR10 and CIFAR100 datasets.
  arXiv  Detail & Related papers  (2023-02-03T02:40:54Z)
• Parametric Classification for Generalized Category Discovery: A Baseline Study [70.73212959385387]
  Generalized Category Discovery (GCD) aims to discover novel categories in unlabelled datasets using knowledge learned from labelled samples. We investigate the failure of parametric classifiers, verify the effectiveness of previous design choices when high-quality supervision is available, and identify unreliable pseudo-labels as a key problem. We propose a simple yet effective parametric classification method that benefits from entropy regularisation, achieves state-of-the-art performance on multiple GCD benchmarks and shows strong robustness to unknown class numbers.
  arXiv  Detail & Related papers  (2022-11-21T18:47:11Z)
• Cluster & Tune: Boost Cold Start Performance in Text Classification [21.957605438780224]
  In real-world scenarios, a text classification task often begins with a cold start, when labeled data is scarce. We suggest a method to boost the performance of such models by adding an intermediate unsupervised classification task.
  arXiv  Detail & Related papers  (2022-03-20T15:29:34Z)
• Self-Certifying Classification by Linearized Deep Assignment [65.0100925582087]
  We propose a novel class of deep predictors for classifying metric data on graphs within PAC-Bayes risk certification paradigm. Building on the recent PAC-Bayes literature and data-dependent priors, this approach enables learning posterior distributions on the hypothesis space.
  arXiv  Detail & Related papers  (2022-01-26T19:59:14Z)
• Interpretable Sequence Classification via Discrete Optimization [26.899228003677138]
  In many applications such as healthcare monitoring or intrusion detection, early classification is crucial to prompt intervention. In this work, we learn sequence classifiers that favour early classification from an evolving observation trace. Our classifiers are interpretable---supporting explanation, counterfactual reasoning, and human-in-the-loop modification.
  arXiv  Detail & Related papers  (2020-10-06T15:31:07Z)
• Solving Long-tailed Recognition with Deep Realistic Taxonomic Classifier [68.38233199030908]
  Long-tail recognition tackles the natural non-uniformly distributed data in realworld scenarios. While moderns perform well on populated classes, its performance degrades significantly on tail classes. Deep-RTC is proposed as a new solution to the long-tail problem, combining realism with hierarchical predictions.
  arXiv  Detail & Related papers  (2020-07-20T05:57:42Z)
• Document Ranking with a Pretrained Sequence-to-Sequence Model [56.44269917346376]
  We show how a sequence-to-sequence model can be trained to generate relevance labels as "target words" Our approach significantly outperforms an encoder-only model in a data-poor regime.
  arXiv  Detail & Related papers  (2020-03-14T22:29:50Z)
• Certified Robustness to Label-Flipping Attacks via Randomized Smoothing [105.91827623768724]
  Machine learning algorithms are susceptible to data poisoning attacks. We present a unifying view of randomized smoothing over arbitrary functions. We propose a new strategy for building classifiers that are pointwise-certifiably robust to general data poisoning attacks.
  arXiv  Detail & Related papers  (2020-02-07T21:28:30Z)

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.