---
title: "From Discrete to Continuous: Progressive Hybrid-Distributional Learning for Gradual Emotion Transitions"
authors:
  - "Yunhe Xie"
  - "Yang Li"
doi: "10.24963/ijcai.2026/411"
url: "https://ijcai.org/proceedings/2026/411"
pdf: "https://ijcai.org/proceedings/2026/0411.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "3691-3699"
track: "Main Track"
keywords:
  - "Natural Language Processing: Sentiment analysis, stylistic analysis, and argument mining"
  - "Natural Language Processing: Dialogue and interactive systems"
  - "Humans and AI: Personalization and user modeling"
  - "Machine Learning: Multi-label learning"
---

# From Discrete to Continuous: Progressive Hybrid-Distributional Learning for Gradual Emotion Transitions

Yunhe Xie, Yang Li

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 3691-3699. DOI: [10.24963/ijcai.2026/411](https://doi.org/10.24963/ijcai.2026/411)

## Abstract

Modeling emotional dynamics in multi-turn dialogues remains challenging due to emotion shifts, where emotional states evolve gradually rather than change abruptly. Existing methods often rely on one-hot supervision, which fails to reflect the progressive nature of human emotions, particularly for neutral-valence emotions with subtle trajectories. To address this limitation, we propose a pseudo soft-label guided Progressive Hybrid-Distributional (PHD) learning framework. PHD reconstructs discrete labels into hybrid distributional representations that encode inter-emotion relations and mixed emotional tendencies. Based on these representations, a progressive training strategy is introduced to guide the model from learning blended emotional states toward the standard one-to-one prediction objective. Furthermore, we design a Graded Contrastive Learning mechanism that replaces rigid binary allocation with graded supervision to alleviate label conflicts. Experiments on benchmark datasets demonstrate PHD consistently improves diverse baseline models, yielding average w-F1 gains of 1.29%. Our framework highlights the critical importance of modeling emotional dynamics as a gradual, distributional process.