WNAR 2024 Research Impact Award Lecture

We propose two methods --- one for supervised learning and the other for unsupervised learning-- both of which make use of an "agreement penalty".

The first—"Cooperative learning"--- is designed for labelled data with multiple sets of features ("views"). The multiview problem is especially important in biology and medicine, where "-omics" data, such as genomics, proteomics, and radiomics, are measured on a common set of samples. Cooperative learning combines the usual squared-error loss of predictions with an "agreement" penalty to encourage the predictions from different data views to agree. By varying the weight of the agreement penalty, we get a continuum of solutions that include the well-known early and late fusion approaches.

Cooperative components analysis ("CoCA") is a new method for unsupervised multi-view analysis. It identifies the component that simultaneously captures significant within-view variance and exhibits strong cross-view correlation. The challenge of integrating multi-view data is particularly important in biology and medicine, where various types of "-omic" data, ranging from genomics to proteomics, are collected from the same set of samples.

CoCA combines a reconstruction error loss to preserve information within data views and an "agreement penalty" to encourage alignment across views. By balancing the trade-off between these two key components in the objective, CoCA encompasses both principal component analysis and canonical correlation analysis as special cases.

This is joint work with DY Ding, S Li, B Narasimhan, Alden Green and Min Sun.