The reviewed record of science sign in
Pith

arxiv: 1904.08049 · v1 · pith:RKBNPXKS · submitted 2019-04-17 · cs.LG · cs.IR· stat.ML

Neural Message Passing for Multi-Label Classification

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:RKBNPXKSrecord.jsonopen to challenge →

classification cs.LG cs.IRstat.ML
keywords lamplabelslabelmessageneuralpassingclassificationdatasets
0
0 comments X
read the original abstract

Multi-label classification (MLC) is the task of assigning a set of target labels for a given sample. Modeling the combinatorial label interactions in MLC has been a long-haul challenge. We propose Label Message Passing (LaMP) Neural Networks to efficiently model the joint prediction of multiple labels. LaMP treats labels as nodes on a label-interaction graph and computes the hidden representation of each label node conditioned on the input using attention-based neural message passing. Attention enables LaMP to assign different importance to neighbor nodes per label, learning how labels interact (implicitly). The proposed models are simple, accurate, interpretable, structure-agnostic, and applicable for predicting dense labels since LaMP is incredibly parallelizable. We validate the benefits of LaMP on seven real-world MLC datasets, covering a broad spectrum of input/output types and outperforming the state-of-the-art results. Notably, LaMP enables intuitive interpretation of how classifying each label depends on the elements of a sample and at the same time rely on its interaction with other labels. We provide our code and datasets at https://github.com/QData/LaMP

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.