4 papers
Oversmoothing, Oversquashing, Heterophily, Long-Range, and more: Demystifying Common Beliefs in Graph Machine Learning
Adrian Arnaiz-Rodriguez, Federico Errica
After a renaissance phase in which researchers revisited the message-passing paradigm through the lens of deep learning, the graph machine learning community shifted its attention…
The Disparate Benefits of Deep Ensembles
Kajetan Schweighofer, Adrian Arnaiz-Rodriguez, Sepp Hochreiter +1
Ensembles of Deep Neural Networks, Deep Ensembles, are widely used as a simple way to boost predictive performance. However, their impact on algorithmic fairness is not well unders…
Structural Group Unfairness: Measurement and Mitigation by means of the Effective Resistance
Adrian Arnaiz-Rodriguez, Georgina Curto, Nuria Oliver
Social networks contribute to the distribution of social capital, defined as the relationships, norms of trust and reciprocity within a community or society that facilitate coopera…
Towards Algorithmic Fairness by means of Instance-level Data Re-weighting based on Shapley Values
Adrian Arnaiz-Rodriguez, Nuria Oliver
Algorithmic fairness is of utmost societal importance, yet state-of-the-art large-scale machine learning models require training with massive datasets that are frequently biased. I…