7 papers
H-SPLID: HSIC-based Saliency Preserving Latent Information Decomposition
Lukas Miklautz, Chengzhi Shi, Andrii Shkabrii +5
We introduce H-SPLID, a novel algorithm for learning salient feature representations through the explicit decomposition of salient and non-salient features into separate spaces. We…
SSplain: Sparse and Smooth Explainer for Retinopathy of Prematurity Classification
Elifnur Sunger, Tales Imbiriba, Peter Campbell +3
Neural networks are frequently used in medical diagnosis. However, due to their black-box nature, model explainers are used to help clinicians understand better and trust model out…
Dependency-aware Maximum Likelihood Estimation for Active Learning
Beyza Kalkanli, Tales Imbiriba, Stratis Ioannidis +2
Active learning aims to efficiently build a labeled training set by strategically selecting samples to query labels from annotators. In this sequential process, each sample acquisi…
Spectral Survival Analysis
Chengzhi Shi, Stratis Ioannidis
Survival analysis is widely deployed in a diverse set of fields, including healthcare, business, ecology, etc. The Cox Proportional Hazard (CoxPH) model is a semi-parametric model…
Fair Concurrent Training of Multiple Models in Federated Learning
Marie Siew, Haoran Zhang, Jong-Ik Park +6
Federated learning (FL) enables collaborative learning across multiple clients. In most FL work, all clients train a single learning task. However, the recent proliferation of FL a…
Learning Set Functions with Implicit Differentiation
Gözde Ãzcan, Chengzhi Shi, Stratis Ioannidis
Ou et al. (2022) introduce the problem of learning set functions from data generated by a so-called optimal subset oracle. Their approach approximates the underlying utility functi…