一句话：提出 CILIATE 框架，用差分分析引导的数据集与训练精炼，同时修复增量学习中的数据集偏置与算法偏置，提升公平性。
深度神经网络面临模型老化问题，需要用增量学习（IL）以新数据加少量旧数据更新模型。基于类的增量学习（CIL）通过更新输出标签避免从头重训并节省旧数据存储，但会导致公平性明显下降。本文指出 CIL 同时存在数据集偏置和算法偏置，现有方法只能部分缓解。为此提出 CILIATE，其核心是差分分析引导的数据集与训练精炼流程：识别现有 CIL 所忽略的独特且重要的样本，并强制模型从这些样本中学习，从而同时修复两类偏置。在三个常用数据集和广泛使用的 ResNet 模型上评估，CILIATE 相比 iCaRL、BiC、WA 分别将公平性提升 17.03%、22.46% 和 31.79%。
Due to the model aging problem, Deep Neural Networks (DNNs) need updates to adjust them to new data distributions. The common practice leverages incremental learning (IL), e.g., Class-based Incremental Learning (CIL) that updates output labels, to update the model with new data and a limited number of old data. This avoids heavyweight training (from scratch) using conventional methods and saves storage space by reducing the number of old data to store. But it also leads to poor performance in fairness. In this paper, we show that CIL suffers both dataset and algorithm bias problems, and existing solutions can only partially solve the problem. We propose a novel framework, CILIATE, that fixes both dataset and algorithm bias in CIL. It features a novel differential analysis guided dataset and training refinement process that identifies unique and important samples overlooked by existing CIL and enforces the model to learn from them. Through this process, CILIATE improves the fairness of CIL by 17.03%, 22.46%, and 31.79% compared to state-of-the-art methods, iCaRL, BiC, and WA, respectively, based on our evaluation on three popular datasets and widely used ResNet models. Our code is available at https://github.com/Antimony5292/CILIATE.
DOI 原文 ·
@inproceedings{paperbot8062,
title = {CILIATE: Towards Fairer Class-Based Incremental Learning by Dataset and Training Refinement},
author = {Xuanqi Gao and Juan Zhai and Shiqing Ma and Chao Shen and Yufei Chen and Shiwei Wang},
booktitle = {ISSTA},
year = {2023},
doi = {10.1145/3597926.3598071}
}