---
title: "On the Generalization of Feature Incremental Learning"
authors:
  - "Chao Xu"
  - "Xijia Tang"
  - "Lijun Zhang"
  - "Chenping Hou"
doi: "10.24963/ijcai.2025/746"
url: "https://ijcai.org/proceedings/2025/746"
pdf: "https://ijcai.org/proceedings/2025/0746.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "6705-6713"
track: "Main Track"
keywords:
  - "Machine Learning: ML: Learning theory"
  - "Machine Learning: ML: Supervised Learning"
---

# On the Generalization of Feature Incremental Learning

Chao Xu, Xijia Tang, Lijun Zhang, Chenping Hou

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 6705-6713. DOI: [10.24963/ijcai.2025/746](https://doi.org/10.24963/ijcai.2025/746)

## Abstract

In many real applications, the data attributes are incremental and the samples are stored with accumulated feature spaces gradually. Although there are several elegant approaches to tackling this problem, the theoretical analysis is still limited. There exist at least two challenges and fundamental questions. 1) How to derive the generalization bounds of these approaches? 2) Under what conditions do these approaches have a strong generalization guarantee? To solve these crucial but rarely studied problems, we provide a comprehensive theoretical analysis in this paper. We begin by summarizing and refining four strategies for addressing feature incremental data. Subsequently, we derive their generalization bounds, providing rigorous and quantitative insights. The theoretical findings highlight the key factors influencing the generalization abilities of different strategies. In tackling the above two fundamental problems, we also provide valuable guidance for exploring other learning challenges in dynamic environments. Finally, the comprehensive experimental and theoretical results mutually validate each other, underscoring the reliability of our conclusions.