{"ID":2893594,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.21119","arxiv_id":"2507.21119","title":"Pre-, In-, and Post-Processing Class Imbalance Mitigation Techniques for Failure Detection in Optical Networks","abstract":"We compare pre-, in-, and post-processing techniques for class imbalance mitigation in optical network failure detection. Threshold Adjustment achieves the highest F1 gain (15.3%), while Random Under-sampling (RUS) offers the fastest inference, highlighting a key performance-complexity trade-off.","short_abstract":"We compare pre-, in-, and post-processing techniques for class imbalance mitigation in optical network failure detection. Threshold Adjustment achieves the highest F1 gain (15.3%), while Random Under-sampling (RUS) offers the fastest inference, highlighting a key performance-complexity trade-off.","url_abs":"https://arxiv.org/abs/2507.21119","url_pdf":"https://arxiv.org/pdf/2507.21119v1","authors":"[\"Yousuf Moiz Ali\",\"Jaroslaw E. Prilepsky\",\"Nicola Sambo\",\"João Pedro\",\"Mohammad M. Hosseini\",\"Antonio Napoli\",\"Sergei K. Turitsyn\",\"Pedro Freire\"]","published":"2025-07-17T16:08:45Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"eess.SP\",\"physics.optics\"]","methods":"[]","has_code":false}