Tech

KINDER: Kernel-based Independence for Fair Representation Learning via Prototype-space Erasure

By Abtin Mogharabin, Alp Toykan Kaplan, Jiaee Cheong, Sinan Kal · arXiv cs.LG

cs.LGstat.ML

arXiv:2611.00264v1 Announce Type: new Abstract: Concept erasure is a prominent approach to achieving fairness in machine learning through the removal of sensitive attributes from learned representations. Prior concept erasure…

Published: November 3, 2026 (6 h ago)
Outlet: arXiv cs.LG
Section: Tech
Length here: Headline and 29-word snippet. The full article is at the source.

More from arXiv cs.LG and around the same time

A semiconductor wafer being lifted from processing equipment

A Framework for Task-Agnostic Counterfactual Fairness in Transformers through Activation SteeringarXiv:2611.00298v1 Announce Type: new Abstract: Bias in transformer-based models is a growing concern as these architectures become more prevalent in automated decision-making systems, such as prediction models for hiring…arXiv cs.LG · 6 h ago · reads at arXiv cs.LG

C3: Speech-Guided KV Retrieval for Long-Context SpeechLLM InferencearXiv:2611.00333v1 Announce Type: new Abstract: Speech language models encode audio at a much higher rate than text, causing the KV cache to dominate the memory, bandwidth, and decoding cost of long-form generation. KV retrieval…arXiv cs.LG · 6 h ago · reads at arXiv cs.LG

Cyber-physical attack detection approaches in the wide-area measurement systemarXiv:2611.00316v1 Announce Type: new Abstract: Improving situational awareness within the Smart Grid is an effective preventive measure to detect potential anomalies, and avoid their adverse consequences. A wide area measurement…arXiv cs.LG · 6 h ago · reads at arXiv cs.LG

DELBERT-2: Pretrained Fingerprint Language Models for DEL Protein Binder PredictionarXiv:2611.00281v1 Announce Type: new Abstract: We present DELBERT-2, a pretrained fingerprint language model that converts sparse molecular fingerprints into unified token sequences using a ModernBERT encoder trained with masked…arXiv cs.LG · 6 h ago · reads at arXiv cs.LG

DEPLOY-RL: Active Boundary Discovery and Conservative Certification for Deployable Reinforcement Learning in Safety-Critical Continuous ProcessesarXiv:2611.00342v1 Announce Type: new Abstract: Reinforcement learning (RL) policies often outperform classical controllers in simulation, yet rarely reach production in safety-critical processes. The barrier is that there is no…arXiv cs.LG · 6 h ago · reads at arXiv cs.LG

Decomposing Irregular Time Series into Interpretable Temporal Patterns with Mixture-of-ExpertsarXiv:2611.00337v1 Announce Type: new Abstract: Irregularly-spaced sequential data, such as transaction logs, encode multi-scale temporal structure that is critical for prediction but difficult to recover explicitly with standard…arXiv cs.LG · 6 h ago · reads at arXiv cs.LG

This page holds the headline and a short snippet as published by arXiv cs.LG, whose feed they came from. The story itself, the photography and the rights stay with them, and the button above goes straight to their site. We keep this page so the headline has a stable address and a record of when it ran.