RoNID: New Intent Discovery with Generated-Reliable Labels and Cluster-friendly Representations

TL;DR

RoNID introduces an EM-style framework for new intent discovery that enhances pseudo-label reliability and representation quality, significantly improving performance on multiple benchmarks.

Contribution

The paper presents a novel EM-style approach combining reliable pseudo-label generation and cluster-friendly representation learning for better intent discovery.

Findings

Achieves +1 to +4 points improvement over state-of-the-art methods.

Effectively constructs high-quality pseudo-labels via optimal transport.

Enhances discriminative features with intra- and inter-cluster contrastive learning.

Abstract

New Intent Discovery (NID) strives to identify known and reasonably deduce novel intent groups in the open-world scenario. But current methods face issues with inaccurate pseudo-labels and poor representation learning, creating a negative feedback loop that degrades overall model performance, including accuracy and the adjusted rand index. To address the aforementioned challenges, we propose a Robust New Intent Discovery (RoNID) framework optimized by an EM-style method, which focuses on constructing reliable pseudo-labels and obtaining cluster-friendly discriminative representations. RoNID comprises two main modules: reliable pseudo-label generation module and cluster-friendly representation learning module. Specifically, the pseudo-label generation module assigns reliable synthetic labels by solving an optimal transport problem in the E-step, which effectively provides high-quality supervised signals for the input of the cluster-friendly representation learning module. To learn cluster-friendly representation with strong intra-cluster compactness and large inter-cluster separation, the representation learning module combines intra-cluster and inter-cluster contrastive learning in the M-step to feed more discriminative features into the generation module. RoNID can be performed iteratively to ultimately yield a robust model with reliable pseudo-labels and cluster-friendly representations. Experimental results on multiple benchmarks demonstrate our method brings substantial improvements over previous state-of-the-art methods by a large margin of +1~+4 points.