Timezone: »

Learning Representations without Compositional Assumptions
Tennison Liu · Jeroen Berrevoets · Zhaozhi Qian · Mihaela van der Schaar

Tue Jul 25 02:00 PM -- 04:30 PM (PDT) @ Exhibit Hall 1 #717
This paper addresses unsupervised representation learning on tabular data containing multiple views generated by distinct sources of measurement. Traditional methods, which tackle this problem using the multi-view framework, are constrained by predefined assumptions that assume feature sets share the same information and representations should learn globally shared factors. However, this assumption is not always valid for real-world tabular datasets with complex dependencies between feature sets, resulting in localized information that is harder to learn. To overcome this limitation, we propose a data-driven approach that learns feature set dependencies by representing feature sets as graph nodes and their relationships as learnable edges. Furthermore, we introduce $\texttt{LEGATO}$, a novel hierarchical graph autoencoder that learns a smaller, latent graph to aggregate information from multiple views dynamically. This approach results in latent graph components that specialize in capturing localized information from different regions of the input, leading to superior downstream performance.

Author Information

Tennison Liu (University of Cambridge)
Jeroen Berrevoets (University of Cambridge)
Zhaozhi Qian (University of Cambridge)
Mihaela van der Schaar (University of Cambridge and UCLA)

More from the Same Authors