Extracting Relationships by Multi-Domain Matching

By Yitong Li, Michael Murias, Geraldine Dawson, David Edwin Carlson. 2018

95 citations recorded by the source corpus.

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.

Subfields: Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

Citations in the corpus

Learning Robust Global Representations by Penalizing Local Predictive Power (2019, methodology): “…invariance via adversarial learning (or further extensions) (Ganin et al., 2016; Bousmalis et al., 2017; Tzeng et al., 2017; Xie et al., 2018; Hoffman et al., 2018; Long et al., 2018; Zhao et al., 2018b; Kumar et al., 2018; Li et al., 2018b; Zhao et al., 2018a; Schoenauer-Sebag et al., 2019).”
Domain Adaptive Ensemble Learning (2020, methodology): “Relationships between sources and target are exploited in [32] where only the target-related sources are kept for model learning.”
Domain Aggregation Networks for Multi-Source Domain Adaptation (2019, methodology): “Although some of them are theoretically motivated with cross-domain generalization bounds, they either use ad-hoc aggregation rules when developing practical algorithms (Zhao et al., 2018; Li et al., 2018) or lack finite-sample analysis (Mansour et al., 2009b;c; Hoffman et al., 2018a).”