Timezone: »

Fast Multi-Resolution Transformer Fine-tuning for Extreme Multi-label Text Classification
Jiong Zhang · Wei-Cheng Chang · Hsiang-Fu Yu · Inderjit Dhillon

Thu Dec 09 08:30 AM -- 10:00 AM (PST) @ None #None

Extreme multi-label text classification~(XMC) seeks to find relevant labels from an extreme large label collection for a given text input. Many real-world applications can be formulated as XMC problems, such as recommendation systems, document tagging and semantic search. Recently, transformer based XMC methods, such as X-Transformer and LightXML, have shown significant improvement over other XMC methods. Despite leveraging pre-trained transformer models for text representation, the fine-tuning procedure of transformer models on large label space still has lengthy computational time even with powerful GPUs. In this paper, we propose a novel recursive approach, XR-Transformer to accelerate the procedure through recursively fine-tuning transformer models on a series of multi-resolution objectives related to the original XMC objective function. Empirical results show that XR-Transformer takes significantly less training time compared to other transformer-based XMC models while yielding better state-of-the-art results. In particular, on the public Amazon-3M dataset with 3 million labels, XR-Transformer is not only 20x faster than X-Transformer but also improves the Precision@1 from 51% to 54%.

Author Information

Jiong Zhang (University of Texas at Austin)
Wei-Cheng Chang (Amazon)
Hsiang-Fu Yu (Amazon)
Inderjit Dhillon (UT Austin & Amazon)

More from the Same Authors