# Decoupling Pseudo Label Disambiguation and Representation Learning for Generalized Intent Discovery

arXiv: https://arxiv.org/abs/2305.17699 · HTML: https://mlsanity.com/paper/2305.17699/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 31 references that are in the map.
- First posted on arXiv 28 May 2023.

## Builds on (most cited first, 24 of 24)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [Generalized Out-of-Distribution Detection: A Survey](https://mlsanity.com/paper/2110.11334/) (2021)
- [Prototypical Contrastive Learning of Unsupervised Representations](https://mlsanity.com/paper/2005.04966/) (2020)
- [Self-labelling via simultaneous clustering and representation learning](https://mlsanity.com/paper/1911.05371/) (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)
- [BERT for Joint Intent Classification and Slot Filling](https://mlsanity.com/paper/1902.10909/) (2019)
- [A Unified Objective for Novel Class Discovery](https://mlsanity.com/paper/2108.08536/) (2021)
- [Discovering New Intents with Deep Aligned Clustering](https://mlsanity.com/paper/2012.08987/) (2020)
- [Deep Unknown Intent Detection with Margin Loss](https://mlsanity.com/paper/1906.00434/) (2019)
- [MoPro: Webly Supervised Learning with Momentum Prototypes](https://mlsanity.com/paper/2009.07995/) (2020)
- [Discovering New Intents via Constrained Deep Adaptive Clustering with Cluster Refinement](https://mlsanity.com/paper/1911.08891/) (2019)
- [Prototypical Verbalizer for Prompt-based Few-shot Tuning](https://mlsanity.com/paper/2203.09770/) (2022)
- [Modeling Discriminative Representations for Out-of-Domain Detection with Supervised Contrastive Learning](https://mlsanity.com/paper/2105.14289/) (2021)
- [Rethinking Supervised Pre-training for Better Downstream Transferring](https://mlsanity.com/paper/2110.06014/) (2021)
- [New Intent Discovery with Pre-training and Contrastive Learning](https://mlsanity.com/paper/2205.12914/) (2022)
- [Semi-supervised Contrastive Learning with Similarity Co-calibration](https://mlsanity.com/paper/2105.07387/) (2021)
- [Bridge to Target Domain by Prototypical Contrastive Learning and Label Confusion: Re-explore Zero-Shot Learning for Slot Filling](https://mlsanity.com/paper/2110.03572/) (2021)
- [Generalized Intent Discovery: Learning from Open World Dialogue System](https://mlsanity.com/paper/2209.06030/) (2022)
- [Watch the Neighbors: A Unified K-Nearest Neighbor Contrastive Learning Framework for OOD Intent Discovery](https://mlsanity.com/paper/2210.08909/) (2022)
- [Disentangling Confidence Score Distribution for Out-of-Domain Intent Detection with Energy-Based Learning](https://mlsanity.com/paper/2210.08830/) (2022)

## Built on by (most cited first, 5 of 5)

- [Beyond the Known: Investigating LLMs Performance on Out-of-Domain Intent Detection](https://mlsanity.com/paper/2402.17256/) (2024)
- [A Survey of Ontology Expansion for Conversational Understanding](https://mlsanity.com/paper/2410.15019/) (2024)
- [Unsupervised Multimodal Clustering for Semantics Discovery in Multimodal Utterances](https://mlsanity.com/paper/2405.12775/) (2024)
- [Integration of Old and New Knowledge for Generalized Intent Discovery: A Consistency-driven Prototype-Prompting Framework](https://mlsanity.com/paper/2506.08490/) (2025)
- [Unlocking Optical Prior: Spectrum-Guided Knowledge Transfer for SAR Generalized Category Discovery](https://mlsanity.com/paper/2604.22174/) (2026)

## Abstract (arXiv)

Generalized intent discovery aims to extend a closed-set in-domain intent classifier to an open-world intent set including in-domain and out-of-domain intents. The key challenges lie in pseudo label disambiguation and representation learning. Previous methods suffer from a coupling of pseudo label disambiguation and representation learning, that is, the reliability of pseudo labels relies on representation learning, and representation learning is restricted by pseudo labels in turn. In this paper, we propose a decoupled prototype learning framework (DPL) to decouple pseudo label disambiguation and representation learning. Specifically, we firstly introduce prototypical contrastive representation learning (PCL) to get discriminative representations. And then we adopt a prototype-based label disambiguation method (PLD) to obtain pseudo labels. We theoretically prove that PCL and PLD work in a collaborative fashion and facilitate pseudo label disambiguation. Experiments and analysis on three benchmark datasets show the effectiveness of our method.