Timezone: »

 
Poster
Controllable Invariance through Adversarial Feature Learning
Qizhe Xie · Zihang Dai · Yulun Du · Eduard Hovy · Graham Neubig

Wed Dec 06 06:30 PM -- 10:30 PM (PST) @ Pacific Ballroom #121
in Posters Wed »

Learning meaningful representations that maintain the content necessary for a particular task while filtering away detrimental variations is a problem of great interest in machine learning. In this paper, we tackle the problem of learning representations invariant to a specific factor or trait of data. The representation learning process is formulated as an adversarial minimax game. We analyze the optimal equilibrium of such a game and find that it amounts to maximizing the uncertainty of inferring the detrimental factor given the representation while maximizing the certainty of making task-specific predictions. On three benchmark tasks, namely fair and bias-free classification, language-independent generation, and lighting-independent image classification, we show that the proposed framework induces an invariant representation, and leads to better generalization evidenced by the improved performance.

Keywords: Supervised Deep Networks · Computer Vision · Adversarial Networks · Natural Language Processing · Denoising
[ Paper] 

Author Information

Qizhe Xie (Carnegie Mellon University)
Zihang Dai (Carnegie Mellon University)
Yulun Du (Carnegie Mellon University)
Eduard Hovy (CMU)
Graham Neubig (Carnegie Mellon University)

More from the Same Authors