On Dyadic Fairness: Exploring and Mitigating Bias in Graph Connections
3. května 2021
Řečníci
Peizhao Li
Řečník · 0 sledujících
Yifei Wang
Řečník · 0 sledujících
Pengyu Hong
Řečník · 0 sledujících
Hongfu Liu
Řečník · 0 sledujících
O prezentaci
Disparate impact has raised serious concerns in machine learning applications and its societal impacts. In response to the need of mitigating discrimination, fairness has been regarded as a crucial property in algorithmic design. In this work, we study the problem of disparate impact on graph-structured data. Specifically, we focus on dyadic fairness, which articulates a fairness concept that a predictive relationship between two instances should be independent of the sensitive attributes. Based on this, we theoretically relate the graph connections to dyadic fairness on link predictive scores in learning graph neural networks, and reveal that regulating weights on existing edges in a graph contributes to dyadic fairness conditionally. Subsequently, we propose our algorithm, \textbf{FairAdj}, to empirically learn a fair adjacency matrix with proper graph structural constraints for fair link prediction, and in the meanwhile preserve predictive accuracy as much as possible. Empirical validation demonstrates that our method delivers effective dyadic fairness in terms of various statistics, and at the same time enjoys a favorable fairness-utility tradeoff.Disparate impact has raised serious concerns in machine learning applications and its societal impacts. In response to the need of mitigating discrimination, fairness has been regarded as a crucial property in algorithmic design. In this work, we study the problem of disparate impact on graph-structured data. Specifically, we focus on dyadic fairness, which articulates a fairness concept that a predictive relationship between two instances should be independent of the sensitive attributes. Based…
O organizátorovi (ICLR 2021)
The International Conference on Learning Representations (ICLR) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence called representation learning, but generally referred to as deep learning. ICLR is globally renowned for presenting and publishing cutting-edge research on all aspects of deep learning used in the fields of artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, text understanding, gaming, and robotics.
Baví vás formát? Nechte SlidesLive zachytit svou akci!
Profesionální natáčení a streamování po celém světě.
Sdílení
Doporučená videa
Prezentace na podobné téma, kategorii nebo přednášejícího
The Geometry of Integration in Text Classification RNNs
Zhlédnout později
Kyle Aitken, …
Babies, brains, objects and words
Zhlédnout později
Domain Generalization with MixStyle
Zhlédnout později
Kaiyang Zhou, …
Enforcing robust control guarantees within neural network policies
Zhlédnout později
Priya Donti, …
Meta-learning in brains and natural intelligence
Zhlédnout později
