Adversarial Constraint Learning for Structured Prediction

05/27/2018
by   Hongyu Ren, et al.
0

Constraint-based learning reduces the burden of collecting labels by having users specify general properties of structured outputs, such as constraints imposed by physical laws. We propose a novel framework for simultaneously learning these constraints and using them for supervision, bypassing the difficulty of using domain expertise to manually specify constraints. Learning requires a black-box simulator of structured outputs, which generates valid labels, but need not model their corresponding inputs or the input-label relationship. At training time, we constrain the model to produce outputs that cannot be distinguished from simulated labels by adversarial training. Providing our framework with a small number of labeled inputs gives rise to a new semi-supervised structured prediction model; we evaluate this model on multiple tasks --- tracking, pose estimation and time series prediction --- and find that it achieves high accuracy with only a small number of labeled inputs. In some cases, no labels are required at all.

READ FULL TEXT
research
05/23/2020

Learning Constraints for Structured Prediction Using Rectifier Networks

Various natural language processing tasks are structured prediction prob...
research
02/13/2018

Predict and Constrain: Modeling Cardinality in Deep Structured Prediction

Many machine learning problems require the prediction of multi-dimension...
research
10/09/2021

RankingMatch: Delving into Semi-Supervised Learning with Consistency Regularization and Ranking Loss

Semi-supervised learning (SSL) has played an important role in leveragin...
research
06/15/2022

Query-Adaptive Predictive Inference with Partial Labels

The cost and scarcity of fully supervised labels in statistical machine ...
research
10/04/2020

Adversarial Attack and Defense of Structured Prediction Models

Building an effective adversarial attacker and elaborating on countermea...
research
12/14/2020

Effective and Efficient Data Poisoning in Semi-Supervised Learning

Semi-Supervised Learning (SSL) aims to maximize the benefits of learning...
research
06/29/2020

Simplifying Models with Unlabeled Output Data

We focus on prediction problems with high-dimensional outputs that are s...

Please sign up or login with your details

Forgot password? Click here to reset