Why be adversarial? Let's cooperate!: Cooperative Dataset Alignment via JSD Upper Bound

Wonwoong Cho, Ziyu Gong, David I. Inouye

Abstract:

Unsupervised dataset alignment estimates a transformation that maps two or more source domains to a shared aligned domain given only the domain datasets.
This task has many applications including generative modeling, unsupervised domain adaptation, and socially aware learning.
Most prior works use adversarial learning (i.e., min-max optimization), which can be challenging to optimize and evaluate.
A few recent works explore non-adversarial flow-based (i.e., invertible) approaches, but they lack a unified perspective.
Therefore, we propose to unify and generalize previous flow-based approaches under a single non-adversarial framework, which we prove is equivalent to minimizing an upper bound on the Jensen-Shannon Divergence (JSD).
Importantly, our problem reduces to a min-min, i.e., cooperative, problem and can provide a natural evaluation metric for unsupervised dataset alignment.
We present empirical results of our framework on both simulated and real-world datasets to demonstrate the benefits of our approach.

One-sentence Summary: We propose non-adversarial unsupervised dataset alignment with invertible flows by proving JSD upper bound.