# Generalized Incremental Learning under Concept Drift across Evolving Data Streams Source: [Generalized Incremental Learning under Concept Drift across Evolving Data Streams]() Collection index: [llms.txt]() Data updated: 2026-03-25T05:00:11.826Z Authors: En Yu, Jie Lu, Guangquan Zhang Published: 2025-06-06T04:36:24.000Z ## Abstract Real-world data streams exhibit inherent non-stationarity characterized by concept drift, posing significant challenges for adaptive learning systems. While existing methods address isolated distribution shifts, they overlook the critical co-evolution of label spaces and distributions under limited supervision and persistent uncertainty. To address this, we formalize Generalized Incremental Learning under Concept Drift (GILCD), characterizing the joint evolution of distributions and label spaces in open-environment streaming contexts, and propose a novel framework called Calibrated Source-Free Adaptation (CSFA). First, CSFA introduces a training-free prototype calibration mechanism that dynamically fuses emerging prototypes with base representations, enabling stable new-class identification without optimization overhead. Second, we design a novel source-free adaptation algorithm, i.e., Reliable Surrogate Gap Sharpness-aware (RSGS) minimization. It integrates sharpness-aware perturbation loss optimization with surrogate gap minimization, while employing entropy-based uncertainty filtering to discard unreliable samples. This mechanism ensures robust distribution alignment and mitigates generalization degradation caused by uncertainties. Thus, CSFA establishes a unified framework for stable adaptation to evolving semantics and distributions in open-world streaming scenarios. Extensive experiments validate the superior performance and effectiveness of CSFA compared to SOTA approaches. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Few-Shot Class Incremental Learning on miniImageNet-C (Session Accuracy)](): Few-Shot Class-Incremental Learning; miniImageNet-C; Session 0 Accuracy: 75.37. - [Few-Shot Class Incremental Learning on CUB200-C (Session Accuracies)](): Few-Shot Class-Incremental Learning; CUB200-C; Session 0 Accuracy: 81.87. - [Few-Shot Class Incremental Learning on CIFAR100-C (Sessions 0-8)](): Few-Shot Class-Incremental Learning; CIFAR100-C; Accuracy (Session 0): 76.55. ## Original sources and implementation [Original paper]() [PDF]()