mlsanityData to 7 Oct 2026

New Intent Discovery with Attracting and Dispersing Prototype

arXiv 2403.16913 ↗First posted 25 Mar 2024cs.CLcited by 6

Not on the map. Why?

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).

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 36 of its 62 references that are in the map. First posted on arXiv 25 Mar 2024.

Builds on

36 of 62 references.

References · 36

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  3. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  4. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  5. 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,393
  6. 2018Deep Clustering for Unsupervised Learning of Visual Featurescited by 1,020
  7. 2015Unsupervised Deep Embedding for Clustering Analysiscited by 763
  8. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 731
  9. 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 691
  10. 2020Prototypical Contrastive Learning of Unsupervised Representationscited by 636
  11. 2019A Theoretical Analysis of Contrastive Unsupervised Representation Learningcited by 530
  12. 2020Efficient Intent Detection with Dual Sentence Encoderscited by 419
24 more
  1. 2019An Evaluation Dataset for Intent Classification and Out-of-Scope Predictioncited by 378
  2. 2016Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clusteringcited by 237
  3. 2019Learning to Discover Novel Visual Categories via Deep Transfer Clusteringcited by 223
  4. 2019Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systemscited by 215
  5. 2021A Unified Objective for Novel Class Discoverycited by 161
  6. 2017Learning to cluster in order to transfer across domains and taskscited by 128
  7. 2019Multi-class Classification without Multi-class Labelscited by 100
  8. 2021Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptationcited by 83
  9. 2021A Broad Study on the Transferability of Visual Representations with Contrastive Learningcited by 78
  10. 2020Discovering New Intents with Deep Aligned Clusteringcited by 68
  11. 2019Discovering New Intents via Constrained Deep Adaptive Clustering with Cluster Refinementcited by 56
  12. 2021Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuningcited by 46
  13. 2024xCoT: Cross-lingual Instruction Tuning for Cross-lingual Chain-of-Thought Reasoningcited by 46
  14. 2022Generalized Category Discovery with Decoupled Prototypical Networkcited by 35
  15. 2021Multilingual Machine Translation Systems from Microsoft for WMT21 Shared Taskcited by 34
  16. 2023IDAS: Intent Discovery with Abstractive Summarizationcited by 22
  17. 2021Generalized Zero-shot Intent Detection via Commonsense Knowledgecited by 21
  18. 2022GanLM: Encoder-Decoder Pre-training with an Auxiliary Discriminatorcited by 20
  19. 2022CROP: Zero-shot Cross-lingual Named Entity Recognition with Multilingual Labeled Sequence Translationcited by 17
  20. 2023mCL-NER: Cross-Lingual Named Entity Recognition via Multi-view Contrastive Learningcited by 14
  21. 2019Low-Resource Response Generation with Template Priorcited by 9
  22. 2023A Clustering Framework for Unsupervised and Semi-supervised New Intent Discoverycited by 9
  23. 2023Improving Self-training for Cross-lingual Named Entity Recognition with Contrastive and Prototype Learningcited by 8
  24. 2023Going beyond research datasets: Novel intent discovery in the industry settingcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 1; 2026: 1.

6 papers.

  1. 2024A Survey of Ontology Expansion for Conversational Understandingcited by 6
  2. 2025H2HTalk: Evaluating Large Language Models as Emotional Companioncited by 3
  3. 2024RoNID: New Intent Discovery with Generated-Reliable Labels and Cluster-friendly Representationscited by 2
  4. 2024Towards Real-world Scenario: Imbalanced New Intent Discoverycited by 2
  5. 2024Unleashing the Potential of Model Bias for Generalized Category Discoverycited by 1
  6. 2026Uncertainty-Aware Continual Learning for Open-World Intent Discovery Under an evolving Label Spacecited by 0