DeepAI AI Chat
Log In Sign Up

Predict and Constrain: Modeling Cardinality in Deep Structured Prediction

by   Nataly Brukhim, et al.
Tel Aviv University

Many machine learning problems require the prediction of multi-dimensional labels. Such structured prediction models can benefit from modeling dependencies between labels. Recently, several deep learning approaches to structured prediction have been proposed. Here we focus on capturing cardinality constraints in such models. Namely, constraining the number of non-zero labels that the model outputs. Such constraints have proven very useful in previous structured prediction approaches, but it is a challenge to introduce them into a deep learning framework. Here we show how to do this via a novel deep architecture. Our approach outperforms strong baselines, achieving state-of-the-art results on multi-label classification benchmarks.


page 1

page 2

page 3

page 4


Structured Prediction Energy Networks

We introduce structured prediction energy networks (SPENs), a flexible f...

Towards Structured Prediction in Bioinformatics with Deep Learning

Using machine learning, especially deep learning, to facilitate biologic...

Interval Type-2 Fuzzy Neural Networks for Multi-Label Classification

Prediction of multi-dimensional labels plays an important role in machin...

Adversarial Constraint Learning for Structured Prediction

Constraint-based learning reduces the burden of collecting labels by hav...

Learning to Predict Combinatorial Structures

The major challenge in designing a discriminative learning algorithm for...

Learning Discriminators as Energy Networks in Adversarial Learning

We propose a novel framework for structured prediction via adversarial l...

Prototype Matching Networks for Large-Scale Multi-label Genomic Sequence Classification

One of the fundamental tasks in understanding genomics is the problem of...