SPRINT: Semi-supervised Prototypical Representation for Few-Shot Class-Incremental Tabular Learning

2026-03-04

AI Summary

This work addresses the challenge of few-shot class-incremental learning on tabular data streams, where labeled data are scarce, new classes emerge continuously, and catastrophic forgetting of previously learned knowledge must be avoided. We propose the first framework specifically designed for few-shot class-incremental learning on tabular data, integrating confidence-guided pseudo-labeling, prototype-based representation learning, and an unconstrained retention strategy for historical base-class data. By leveraging the low storage overhead and abundant unlabeled samples inherent to tabular data, our approach eliminates reliance on replay buffers. Evaluated on six cross-domain tabular benchmarks under a 5-shot setting, the method achieves an average accuracy of 77.37%, significantly outperforming the strongest incremental baseline by 4.45%, thereby demonstrating its effectiveness and generalizability.

Technology Category

• Machine Learning: Life-Long and Continual Learning
• Search and Optimization: Learning to Search
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Real-world systems must continuously adapt to novel concepts from limited data without forgetting previously acquired knowledge. While Few-Shot Class-Incremental Learning (FSCIL) is established in computer vision, its application to tabular domains remains largely unexplored. Unlike images, tabular streams (e.g., logs, sensors) offer abundant unlabeled data, a scarcity of expert annotations and negligible storage costs, features ignored by existing vision-based methods that rely on restrictive buffers. We introduce SPRINT, the first FSCIL framework tailored for tabular distributions. SPRINT introduces a mixed episodic training strategy that leverages confidence-based pseudo-labeling to enrich novel class representations and exploits low storage costs to retain base class history. Extensive evaluation across six diverse benchmarks spanning cybersecurity, healthcare, and ecological domains, demonstrates SPRINT's cross-domain robustness. It achieves a state-of-the-art average accuracy of 77.37% (5-shot), outperforming the strongest incremental baseline by 4.45%.

Problem

• Few-Shot Class-Incremental Learning
• Tabular Data
• Semi-supervised Learning
• Continual Learning
• Class-Incremental

Innovation

• Few-Shot Class-Incremental Learning
• Tabular Data
• Semi-supervised Learning
• Pseudo-labeling
• Prototypical Representation