Extracting Relationships by Multi-Domain Matching

Abstract

In many biological and medical contexts, we construct a large labeled corpus by aggregating many sources to use in target prediction tasks. Unfortunately, many of the sources may be irrelevant to our target task, so ignoring the structure of the dataset is detrimental. This work proposes a novel approach, the Multiple Domain Matching Network (MDMN), to exploit this structure. MDMN embeds all data into a shared feature space while learning which domains share strong statistical relationships. These relationships are often insightful in their own right, and they allow domains to share strength without interference from irrelevant data. This methodology builds on existing distribution-matching approaches by assuming that source domains are varied and outcomes multi-factorial. Therefore, each domain should only match a relevant subset. Theoretical analysis shows that the proposed approach can have a tighter generalization bound than existing multiple-domain adaptation approaches. Empirically, we show that the proposed methodology handles higher numbers of source domains (up to 21 empirically), and provides state-of-the-art performance on image, text, and multi-channel time series classification, including clinical outcome data in an open label trial evaluating a novel treatment for Autism Spectrum Disorder.

Figure 1:

Figure 1(a) visualizes previous multiple-domain adaptation methods. Figure 1(b) visualizes the proposed method, with domain adaptation between all domains.

Figure 2:

Figure 2 is a visualization of the graph induced on 22 patients by the proposed model, MDMN. Each node represents one subject and the target domain is shown in blue. Note that although the target is only strongly connected to one source domain, the links between source domains allow them to share strength and make more robust predictions. The lines are labeled by the mean of the directional weights learned in MDMN.

Figure 3:

The framework of MDMN.

Figure 4:

Visualization of feature spaces of different models by t-SNE. Each color represents one dataset of MNIST, MNISTM, SVHN and USPS. The testing target domain is MNISTM. The digit label is shown in the plot. The goal is to adapt generalized feature from source domains to the target domains; the digits should cluster together rather than the color clustering.

Figure 5:

Relative classification accuracy by subject on two EEG datasets. The accuracy without subtracting the baseline performance is given in appendix C.2.