Learning Assistance from an Adversarial Critic for Multi-Outputs Prediction

Yue Deng, Yilin Shen, Hongxia Jin

Introduction

Predicting multiple structured outputs—such as multi-label image tagging or sequence-to-sequence translation—remains a significant challenge in machine learning due to the complex interdependencies between output variables. While adversarial learning (GANs) has introduced "critics" to evaluate output quality, these critics typically provide only a single scalar score. This limited feedback fails to capture the rich, structural information necessary for a model to understand why a prediction was suboptimal.

The Adversarial Critic and Assistant (ACA) Framework

To address this, the authors propose the Adversarial-Critic-and-Assistant (ACA) framework. ACA introduces a collaborative "Assistant" module that bridges the gap between the Critic's evaluation and the Predictor's refinement process.

The framework operates through three primary components:

  1. The Predictor: Generates the initial multi-output prediction from the input data.
  2. The Critic: Evaluates the compatibility between the input and the prediction. It utilizes a "compatibility fusion layer" to encode deep structural insights.
  3. The Assistant: Extracts information from the Critic’s fusion layer and final score to generate a dense help vector.
The ACA framework (a), its recurrent unfolding (b), and internal predictor details (c).

The Predictor then uses this help vector to iteratively refine its output. This process is unfolded over $T$ time steps, allowing the model to "learn from its mistakes" in a manner analogous to a student receiving detailed feedback from a teaching assistant. Importantly, ACA is framework-agnostic and can be applied to various existing architectures.

Experimental Results

The ACA framework was evaluated across diverse domains, including document modeling, image attribute prediction, and logic form generation.

  • Multi-label Classification: On the 'Delicious' document dataset, ACA improved the Macro F1 score of the base BPMLL model from 38.3% to 40.2%. Similar gains were observed in image tasks; for the NUS-wide dataset, Macro F1 rose from 61.8% to 67.0%.
  • Sequence-to-Sequence: In logic form generation (ATIS dataset), ACA achieved 85.2% accuracy, outperforming standard attention models (82.0%) and reinforcement-learning-based critics like SeqGAN (82.7%).

Analysis of Iterative Refinement

A key feature of ACA is its iterative nature. By increasing the number of recurrent steps $T$, the model can achieve higher accuracy as it continuously refines its predictions based on the Assistant's feedback.

Performance metrics and time costs across different recurrent steps T on CUB and ATIS datasets.

As shown in the experimental analysis, performance generally improves with $T$, though computational costs increase linearly. The authors identify $T=5$ as an optimal balance between performance gains and efficiency, as further iterations yield diminishing returns relative to the time cost.

Conclusion

The ACA framework provides a versatile, plug-and-play wrapper for existing multi-output models. By transforming scalar adversarial scores into dense, actionable feedback, it significantly enhances the learning of complex output structures. While currently less effective for single-output tasks, its success in multi-label and seq2seq domains marks a significant step forward in structured prediction.

Summary updated

Abstract

We introduce an adversarial-critic-and-assistant (ACA) learning framework to improve the performance of existing supervised learning with multiple outputs. The core contribution of our ACA is the innovation of two novel modules, i.e. an `adversarial critic' and a `collaborative assistant', that are jointly designed to provide augmenting information for facilitating general learning tasks. Our approach is not intended to be regarded as an emerging competitor for tons of well-established algorithms in the field. In fact, most existing approaches, while implemented with different learning objectives, can all be adopted as building blocks seamlessly integrated in the ACA framework to accomplish various real-world tasks. We show the performance and generalization ability of ACA on diverse learning tasks including multi-label classification, attributes prediction and sequence-to-sequence generation.
BibTeX
@inproceedings{deng2019learning,
  author = {Yue Deng and Yilin Shen and Hongxia Jin},
  title = {{Learning Assistance from an Adversarial Critic for Multi-Outputs Prediction}},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year = {2019},
  doi = {10.24963/ijcai.2019/688},
}
Figure