# New Intent Discovery with Attracting and Dispersing Prototype

arXiv: https://arxiv.org/abs/2403.16913 · HTML: https://mlsanity.com/paper/2403.16913/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 62 references that are in the map.
- First posted on arXiv 25 Mar 2024.

## Builds on (most cited first, 30 of 36)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere](https://mlsanity.com/paper/2005.10242/) (2020)
- [Deep Clustering for Unsupervised Learning of Visual Features](https://mlsanity.com/paper/1807.05520/) (2018)
- [Unsupervised Deep Embedding for Clustering Analysis](https://mlsanity.com/paper/1511.06335/) (2015)
- [This Looks Like That: Deep Learning for Interpretable Image Recognition](https://mlsanity.com/paper/1806.10574/) (2018)
- [DivideMix: Learning with Noisy Labels as Semi-supervised Learning](https://mlsanity.com/paper/2002.07394/) (2020)
- [Prototypical Contrastive Learning of Unsupervised Representations](https://mlsanity.com/paper/2005.04966/) (2020)
- [A Theoretical Analysis of Contrastive Unsupervised Representation Learning](https://mlsanity.com/paper/1902.09229/) (2019)
- [Efficient Intent Detection with Dual Sentence Encoders](https://mlsanity.com/paper/2003.04807/) (2020)
- [An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction](https://mlsanity.com/paper/1909.02027/) (2019)
- [Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering](https://mlsanity.com/paper/1610.04794/) (2016)
- [Learning to Discover Novel Visual Categories via Deep Transfer Clustering](https://mlsanity.com/paper/1908.09884/) (2019)
- [Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems](https://mlsanity.com/paper/1905.08743/) (2019)
- [A Unified Objective for Novel Class Discovery](https://mlsanity.com/paper/2108.08536/) (2021)
- [Learning to cluster in order to transfer across domains and tasks](https://mlsanity.com/paper/1711.10125/) (2017)
- [Multi-class Classification without Multi-class Labels](https://mlsanity.com/paper/1901.00544/) (2019)
- [Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptation](https://mlsanity.com/paper/2103.16765/) (2021)
- [A Broad Study on the Transferability of Visual Representations with Contrastive Learning](https://mlsanity.com/paper/2103.13517/) (2021)
- [Discovering New Intents with Deep Aligned Clustering](https://mlsanity.com/paper/2012.08987/) (2020)
- [Discovering New Intents via Constrained Deep Adaptive Clustering with Cluster Refinement](https://mlsanity.com/paper/1911.08891/) (2019)
- [Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuning](https://mlsanity.com/paper/2109.06349/) (2021)
- [xCoT: Cross-lingual Instruction Tuning for Cross-lingual Chain-of-Thought Reasoning](https://mlsanity.com/paper/2401.07037/) (2024)
- [Generalized Category Discovery with Decoupled Prototypical Network](https://mlsanity.com/paper/2211.15115/) (2022)
- [Multilingual Machine Translation Systems from Microsoft for WMT21 Shared Task](https://mlsanity.com/paper/2111.02086/) (2021)
- [IDAS: Intent Discovery with Abstractive Summarization](https://mlsanity.com/paper/2305.19783/) (2023)
- [Generalized Zero-shot Intent Detection via Commonsense Knowledge](https://mlsanity.com/paper/2102.02925/) (2021)
- [GanLM: Encoder-Decoder Pre-training with an Auxiliary Discriminator](https://mlsanity.com/paper/2212.10218/) (2022)

## Built on by (most cited first, 6 of 6)

- [A Survey of Ontology Expansion for Conversational Understanding](https://mlsanity.com/paper/2410.15019/) (2024)
- [H2HTalk: Evaluating Large Language Models as Emotional Companion](https://mlsanity.com/paper/2507.03543/) (2025)
- [RoNID: New Intent Discovery with Generated-Reliable Labels and Cluster-friendly Representations](https://mlsanity.com/paper/2404.08977/) (2024)
- [Towards Real-world Scenario: Imbalanced New Intent Discovery](https://mlsanity.com/paper/2406.03127/) (2024)
- [Unleashing the Potential of Model Bias for Generalized Category Discovery](https://mlsanity.com/paper/2412.12501/) (2024)
- [Uncertainty-Aware Continual Learning for Open-World Intent Discovery Under an evolving Label Space](https://mlsanity.com/paper/2609.17866/) (2026)

## Abstract (arXiv)

New Intent Discovery (NID) aims to recognize known and infer new intent categories with the help of limited labeled and large-scale unlabeled data. The task is addressed as a feature-clustering problem and recent studies augment instance representation. However, existing methods fail to capture cluster-friendly representations, since they show less capability to effectively control and coordinate within-cluster and between-cluster distances. Tailored to the NID problem, we propose a Robust and Adaptive Prototypical learning (RAP) framework for globally distinct decision boundaries for both known and new intent categories. Specifically, a robust prototypical attracting learning (RPAL) method is designed to compel instances to gravitate toward their corresponding prototype, achieving greater within-cluster compactness. To attain larger between-cluster separation, another adaptive prototypical dispersing learning (APDL) method is devised to maximize the between-cluster distance from the prototype-to-prototype perspective. Experimental results evaluated on three challenging benchmarks (CLINC, BANKING, and StackOverflow) of our method with better cluster-friendly representation demonstrate that RAP brings in substantial improvements over the current state-of-the-art methods (even large language model) by a large margin (average +5.5% improvement).