{"ID":5937010,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-09T15:05:50.046563074Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.05201","arxiv_id":"2607.05201","title":"FlatManifold: Robust Continual Learning under Severe Label Noise and Domain Shifts via Intrinsic Manifold Flattening","abstract":"In non-stationary streaming environments, simultaneously adapting to complex, non-linear domain shifts via continual learning while mitigating the catastrophic effects of severe, uncalibrated label noise poses a fundamental mathematical challenge. In this paper, we propose \\FlatManifold{}, a novel, streamlined robust continual learning framework that utilizes a Nyström manifold flattening map based on the kernel trick and projection onto an orthogonalized Reproducing Kernel Hilbert Space (RKHS). Unlike traditional methods that rely on complex, error-prone sample-filtering pipelines, the proposed approach exploits the intrinsic mathematical robustness of the flattened space itself. By mapping feature distributions onto a fixed orthogonal target topology with a ridge regularizer, the framework naturally smoothes and counteracts the influence of extreme label noise during the optimization process. Concurrently, catastrophic forgetting is prevented via a continual topology brake term that leverages the covariance matrix of past experiences. Extensive evaluation on real-world multi-session robotics datasets demonstrates that even under severe conditions featuring 40\\% symmetric label noise, \\FlatManifold{} successfully mitigates gradient corruption. Under extreme cross-session domain shifts spanning various seasons and lighting conditions, the proposed framework establishes high generalization capabilities, significantly outperforming standard sequential optimization baselines and proving that structural linearization itself serves as a powerful mathematical barrier against distributed label corruption.","short_abstract":"In non-stationary streaming environments, simultaneously adapting to complex, non-linear domain shifts via continual learning while mitigating the catastrophic effects of severe, uncalibrated label noise poses a fundamental mathematical challenge. In this paper, we propose \\FlatManifold{}, a novel, streamlined robust c...","url_abs":"https://arxiv.org/abs/2607.05201","url_pdf":"https://arxiv.org/pdf/2607.05201v1","authors":"[\"Rai Hisada\",\"Kanji Tanaka\"]","published":"2026-07-06T15:17:01Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[]","has_code":false}