🤖 AI Summary
This work addresses the dual challenges of severe uncalibrated label noise and complex nonlinear domain shifts in non-stationary streaming scenarios by proposing a robust continual learning framework based on Nyström manifold flattening mappings. Departing from conventional sample filtering strategies, the method leverages kernel tricks to project feature distributions into an orthogonalized reproducing kernel Hilbert space (RKHS), integrating ridge regularization with a covariance-based topological braking term to structurally suppress label noise and mitigate catastrophic forgetting during optimization. Evaluated on real-world robotic multi-session data featuring 40% symmetric label noise and drastic cross-seasonal illumination changes, the approach significantly outperforms existing baselines, effectively alleviating gradient contamination while achieving high generalization performance.
📝 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.