LaFiCMIL: Rethinking Large File Classification from the Perspective of Correlated Multiple Instance Learning

TL;DR

LaFiCMIL is a novel large file classification method leveraging correlated multiple instance learning, enabling efficient, high-performance classification of lengthy documents on a single GPU, surpassing existing models in benchmarks.

Contribution

Introduces LaFiCMIL, a new approach for large file classification that efficiently scales BERT to nearly 20,000 tokens on a single GPU, with state-of-the-art results.

Findings

Achieves new benchmarks across seven datasets.

Scales BERT to handle nearly 20,000 tokens on a single GPU.

Operates efficiently for binary, multi-class, and multi-label tasks.

Abstract

Transfomer-based models have significantly advanced natural language processing, in particular the performance in text classification tasks. Nevertheless, these models face challenges in processing large files, primarily due to their input constraints, which are generally restricted to hundreds or thousands of tokens. Attempts to address this issue in existing models usually consist in extracting only a fraction of the essential information from lengthy inputs, while often incurring high computational costs due to their complex architectures. In this work, we address the challenge of classifying large files from the perspective of correlated multiple instance learning. We introduce LaFiCMIL, a method specifically designed for large file classification. LaFiCMIL is optimized for efficient operation on a single GPU, making it a versatile solution for binary, multi-class, and multi-label classification tasks. We conducted extensive experiments using seven diverse and comprehensive benchmark datasets to assess LaFiCMIL's effectiveness. By integrating BERT for feature extraction, LaFiCMIL demonstrates exceptional performance, setting new benchmarks across all datasets. A notable achievement of our approach is its ability to scale BERT to handle nearly 20,000 tokens while operating on a single GPU with 32GB of memory. This efficiency, coupled with its state-of-the-art performance, highlights LaFiCMIL's potential as a groundbreaking approach in the field of large file classification.