A Diffusion Weighted Graph Framework for New Intent Discovery

TL;DR

This paper introduces a Diffusion Weighted Graph Framework that leverages semantic and structural data relationships to improve new intent discovery, outperforming existing methods on benchmark datasets.

Contribution

The paper proposes a novel graph-based framework with diffusion and smoothing techniques to better utilize data structure for intent discovery.

Findings

Outperforms state-of-the-art models on multiple datasets

Effectively captures semantic and structural relationships

Reduces noise in ambiguous samples

Abstract

New Intent Discovery (NID) aims to recognize both new and known intents from unlabeled data with the aid of limited labeled data containing only known intents. Without considering structure relationships between samples, previous methods generate noisy supervisory signals which cannot strike a balance between quantity and quality, hindering the formation of new intent clusters and effective transfer of the pre-training knowledge. To mitigate this limitation, we propose a novel Diffusion Weighted Graph Framework (DWGF) to capture both semantic similarities and structure relationships inherent in data, enabling more sufficient and reliable supervisory signals. Specifically, for each sample, we diffuse neighborhood relationships along semantic paths guided by the nearest neighbors for multiple hops to characterize its local structure discriminately. Then, we sample its positive keys and weigh them based on semantic similarities and local structures for contrastive learning. During inference, we further propose Graph Smoothing Filter (GSF) to explicitly utilize the structure relationships to filter high-frequency noise embodied in semantically ambiguous samples on the cluster boundary. Extensive experiments show that our method outperforms state-of-the-art models on all evaluation metrics across multiple benchmark datasets. Code and data are available at https://github.com/yibai-shi/DWGF.