paper-with-me

홈 › Papers

A Unifying Post-Processing Framework for Multi-Objective Learn-to-Defer Problems

2024-07-17 · Mohammad-Amin Charusaie, Samira Samadi

Learn-to-Defer is a paradigm that enables learning algorithms to work not in isolation but as a team with human experts. In this paradigm, we permit the system to defer a subset of its tasks to the expert. Although there are currently systems that follow this paradigm and are designed to optimize the accuracy of the final human-AI team, the general methodology for developing such systems under a set of constraints (e.g., algorithmic fairness, expert intervention budget, defer of anomaly, etc.) remains largely unexplored. In this paper, using a $d$-dimensional generalization to the fundamental lemma of Neyman and Pearson (d-GNP), we obtain the Bayes optimal solution for learn-to-defer systems under various constraints. Furthermore, we design a generalizable algorithm to estimate that solution and apply this algorithm to the COMPAS and ACSIncome datasets. Our algorithm shows improvements in terms of constraint violation over a set of baselines.

📄 PDF Abstract BibTeX arXiv:2407.12710

Code (1)

aminchrs/postprocess 공식 구현 pytorch

Tasks

FairnessLEMMA

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Post-Training in Time Series Foundation Models: A Unifying Framework

2026-07-22 · Shifeng Xie, Ambroise Odonnat, Zehao Xiao, Lei Zan 외 arxiv

Time series foundation models (TSFMs) have emerged as general-purpose models for time series analysis, but pretraining alone is often insufficient for reliable downstream deployment. Bridging this gap requires further in…

Time Series Analysis

A Unifying Bayesian View of Continual Learning

2019-02-18 · Sebastian Farquhar, Yarin Gal

Some machine learning applications require continual learning - where data comes in a sequence of datasets, each is used for training and then permanently discarded. From a Bayesian perspective, continual learning seems …

Continual Learning

Bridging Multicalibration and Out-of-distribution Generalization Beyond Covariate Shift

2024-06-02 · Jiayun Wu, Jiashuo Liu, Peng Cui, Zhiwei Steven Wu

We establish a new model-agnostic optimization framework for out-of-distribution generalization via multicalibration, a criterion that ensures a predictor is calibrated across a family of overlapping groups. Multicalibra…

Out-of-Distribution Generalization

Unifying Post-hoc Explanations of Knowledge Graph Completions

2025-07-29 · Alessandro Lonardi, Samy Badreddine, Tarek R. Besold, Pablo Sanchez Martin arxiv

Knowledge Graphs organize information as entity-relation-entity triples, enabling machine learning models to predict plausible missing triples in a task known as Knowledge Graph Completion (KGC). Post-hoc explainability …

Knowledge Graph CompletionKnowledge Graphs

Metanetworks as Regulatory Operators: Learning to Edit for Requirement Compliance

2025-12-17 · Ioannis Kalogeropoulos, Giorgos Bouritsas, Yannis Panagakis arxiv

As machine learning models are increasingly deployed in high-stakes settings, e.g. as decision support systems in various societal sectors or in critical infrastructure, designers and auditors are facing the need to ensu…