Towards Interpretable Deep Extreme Multi-label Learning

2019-07-03 · Yihuang Kang, I-Ling Cheng, Wenjui Mao, Bowen Kuo, Pei-Ju Lee

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.

📄 PDF Abstract BibTeX arXiv:1907.01723

Code (0)

등록된 구현이 없습니다.

Tasks

BIG-bench Machine Learning Multi-Label Learning

Methods 이 논문이 사용한 방법론

Interpretability 설명 없음

Solana Customer Service Number +1-833-534-1729 설명 없음

Graphite: A Graph-based Extreme Multi-Label Short Text Classifier for Keyphrase Recommendation

2024-07-29 · Ashirbad Mishra, Soumik Dey, Jinyu Zhao, Marshall Wu 외

Keyphrase Recommendation has been a pivotal problem in advertising and e-commerce where advertisers/sellers are recommended keyphrases (search queries) to bid on to increase their sales. It is a challenging task due to t…

GPU text-classification Text Classification

DILA: Dictionary Label Attention for Mechanistic Interpretability in High-dimensional Multi-label Medical Coding Prediction

2024-09-16 · John Wu, David Wu, Jimeng Sun

Predicting high-dimensional or extreme multilabels, such as in medical coding, requires both accuracy and interpretability. Existing works often rely on local interpretability methods, failing to provide comprehensive ex…

Diffuse to Detect: Generative Diffusion Models for Unsupervised IC Anomaly Detection

2026-05-26 · Yuxuan Yin, Chen He, Todd Jacobs, Jialei He 외 arxiv

Latent defect screening is challenged by extremely low failure rates, high-dimensional test data, and absence of labeled anomalies. We propose the first unsupervised anomaly detection framework incorporating a Diffusion …

Unsupervised Anomaly Detection Feature Engineering

Pseudo Label NCF for Sparse OHC Recommendation: Dual Representation Learning and the Separability Accuracy Trade off

2026-03-25 · Pronob Kumar Barman, Tera L. Reynolds, James Foulds arxiv

Online Health Communities connect patients for peer support, but users face a discovery challenge when they have minimal prior interactions to guide personalization. We study recommendation under extreme interaction spar…

Collaborative Filtering Representation Learning

Adopting the Multi-answer Questioning Task with an Auxiliary Metric for Extreme Multi-label Text Classification Utilizing the Label Hierarchy

2023-03-02 · Li Wang, Ying Wah Teh, Mohammed Ali Al-Garadi

Extreme multi-label text classification utilizes the label hierarchy to partition extreme labels into multiple label groups, turning the task into simple multi-group multi-label classification tasks. Current research enc…

Classification Extreme Multi-Label Classification Multi-Label Classification MUlTI-LABEL-ClASSIFICATION+5