Towards Interpretable Deep Extreme Multi-label Learning

07/03/2019
by   Yihuang Kang, et al.
16

Many Machine Learning algorithms, such as deep neural networks, have long been criticized for being "black-boxes"-a kind of models unable to provide how it arrive at a decision without further efforts to interpret. This problem has raised concerns on model applications' trust, safety, nondiscrimination, and other ethical issues. In this paper, we discuss the machine learning interpretability of a real-world application, eXtreme Multi-label Learning (XML), which involves learning models from annotated data with many pre-defined labels. We propose a two-step XML approach that combines deep non-negative autoencoder with other multi-label classifiers to tackle different data applications with a large number of labels. Our experimental result shows that the proposed approach is able to cope with many-label problems as well as to provide interpretable label hierarchies and dependencies that helps us understand how the model recognizes the existences of objects in an image.

READ FULL TEXT

page 2

page 5

research
08/30/2016

Multi-Label Classification Method Based on Extreme Learning Machines

In this paper, an Extreme Learning Machine (ELM) based technique for Mul...
research
08/31/2016

A Novel Online Real-time Classifier for Multi-label Data Streams

In this paper, a novel extreme learning machine based online multi-label...
research
11/23/2020

The Emerging Trends of Multi-Label Learning

Exabytes of data are generated daily by humans, leading to the growing n...
research
07/16/2023

SHAMSUL: Simultaneous Heatmap-Analysis to investigate Medical Significance Utilizing Local interpretability methods

The interpretability of deep neural networks has become a subject of gre...
research
07/28/2021

XFL: eXtreme Function Labeling

Reverse engineers would benefit from identifiers like function names, bu...
research
10/08/2022

A Survey on Extreme Multi-label Learning

Multi-label learning has attracted significant attention from both acade...
research
09/09/2022

Estimating Multi-label Accuracy using Labelset Distributions

A multi-label classifier estimates the binary label state (relevant vs i...

Please sign up or login with your details

Forgot password? Click here to reset