1 code implementation • 5 Dec 2023 • Miriam Rateike, Celia Cintas, John Wamburu, Tanya Akumu, Skyler Speakman
We introduce a weakly supervised auditing technique using a subset scanning approach to detect anomalous patterns in LLM activations from pre-trained models.
no code implementations • 21 Nov 2023 • Miriam Rateike, Isabel Valera, Patrick Forré
Neglecting the effect that decisions have on individuals (and thus, on the underlying data distribution) when designing algorithmic decision-making policies may increase inequalities and unfairness in the long term - even if fairness considerations were taken in the policy design process.
1 code implementation • 10 May 2022 • Miriam Rateike, Ayan Majumdar, Olga Mineeva, Krishna P. Gummadi, Isabel Valera
In addition, data is often selectively labeled, i. e., even the biased labels are only observed for a small fraction of the data that received a positive decision.
1 code implementation • 27 Oct 2021 • Pablo Sanchez-Martin, Miriam Rateike, Isabel Valera
In this paper, we introduce VACA, a novel class of variational graph autoencoders for causal inference in the absence of hidden confounders, when only observational data and the causal graph are available.
no code implementations • NeurIPS 2021 • Pablo Sanchez Martin, Miriam Rateike, Isabel Valera
We propose the Variational Causal Autoencoder (VCAUSE), a novel class of variational graph autoencoders for causal inference in the absence of hidden confounders, when only observational data and the causal graph are available.