Open World Classification with Adaptive Negative Samples

TL;DR

This paper introduces ANS, a novel method for open world classification that generates synthetic negative samples during training, improving the model's ability to distinguish known from unknown classes without external data.

Contribution

The paper proposes an adaptive negative sampling approach that enhances open world classification by generating effective training samples without prior knowledge.

Findings

ANS outperforms existing methods on benchmark datasets.

Auxiliary one-vs-rest classifiers improve open category detection.

Synthetic negative samples enhance decision boundary learning.

Abstract

Open world classification is a task in natural language processing with key practical relevance and impact. Since the open or {\em unknown} category data only manifests in the inference phase, finding a model with a suitable decision boundary accommodating for the identification of known classes and discrimination of the open category is challenging. The performance of existing models is limited by the lack of effective open category data during the training stage or the lack of a good mechanism to learn appropriate decision boundaries. We propose an approach based on \underline{a}daptive \underline{n}egative \underline{s}amples (ANS) designed to generate effective synthetic open category samples in the training stage and without requiring any prior knowledge or external datasets. Empirically, we find a significant advantage in using auxiliary one-versus-rest binary classifiers, which effectively utilize the generated negative samples and avoid the complex threshold-seeking stage in previous works. Extensive experiments on three benchmark datasets show that ANS achieves significant improvements over state-of-the-art methods.