Out-of-Distribution Detection through Soft Clustering with Non-Negative Kernel Regression
Abstract: As language models become more general purpose, increased attention needs to be paid to detecting out-of-distribution (OOD) instances, i.e., those not belonging to any of the distributions seen during training. Existing methods for detecting OOD data are computationally complex and storage-intensive. We propose a novel soft clustering approach for OOD detection based on non-negative kernel regression. Our approach greatly reduces computational and space complexities (up to $11\times $ improvement in inference time and 87% reduction in storage requirements) and outperforms existing approaches by up to 4 AUROC points on four different benchmarks. We also introduce an entropy-constrained version of our algorithm, which leads to further reductions in storage requirements (up to 97\% lower than comparable approaches) while retaining competitive performance. Our soft clustering approach for OOD detection highlights its potential for detecting tail-end phenomena in extreme-scale data settings.
Paper Type: Long
Research Area: Machine Learning for NLP
Research Area Keywords: graph-based methods, contrastive learning
Contribution Types: Approaches low compute settings-efficiency, Publicly available software and/or pre-trained models
Languages Studied: English
Submission Number: 4198
Loading