Light-weight Deep Extreme Multilabel Classification

04/20/2023
by   Istasis Mishra, et al.
0

Extreme multi-label (XML) classification refers to the task of supervised multi-label learning that involves a large number of labels. Hence, scalability of the classifier with increasing label dimension is an important consideration. In this paper, we develop a method called LightDXML which modifies the recently developed deep learning based XML framework by using label embeddings instead of feature embedding for negative sampling and iterating cyclically through three major phases: (1) proxy training of label embeddings (2) shortlisting of labels for negative sampling and (3) final classifier training using the negative samples. Consequently, LightDXML also removes the requirement of a re-ranker module, thereby, leading to further savings on time and memory requirements. The proposed method achieves the best of both worlds: while the training time, model size and prediction times are on par or better compared to the tree-based methods, it attains much better prediction accuracy that is on par with the deep learning based methods. Moreover, the proposed approach achieves the best tail-label prediction accuracy over most state-of-the-art XML methods on some of the large datasets[accepted in IJCNN 2023, partial funding from MAPG grant and IIIT Seed grant at IIIT, Hyderabad, India. Code: <https://github.com/misterpawan/LightDXML>]

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/17/2019

Bonsai - Diverse and Shallow Trees for Extreme Multi-label Classification

Extreme multi-label classification refers to supervised multi-label lear...
research
01/09/2021

LightXML: Transformer with Dynamic Negative Sampling for High-Performance Extreme Multi-label Text Classification

Extreme Multi-label text Classification (XMC) is a task of finding the m...
research
12/17/2019

An Embarrassingly Simple Baseline for eXtreme Multi-label Prediction

The goal of eXtreme Multi-label Learning (XML) is to design and learn a ...
research
02/12/2023

Review of Extreme Multilabel Classification

Extreme multilabel classification or XML, in short, has emerged as a new...
research
10/28/2017

Label Embedding Network: Learning Label Representation for Soft Training of Deep Networks

We propose a method, called Label Embedding Network, which can learn lab...
research
09/18/2017

Leveraging Distributional Semantics for Multi-Label Learning

We present a novel and scalable label embedding framework for large-scal...
research
05/31/2023

Label Embedding by Johnson-Lindenstrauss Matrices

We present a simple and scalable framework for extreme multiclass classi...

Please sign up or login with your details

Forgot password? Click here to reset