Research map / Graph learning / Knowledge and temporal graphs
Multivariate, Multi-Frequency and Multimodal: Rethinking Graph Neural Networks for Emotion Recognition in Conversation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use M3Net's multivariate and multi-frequency propagation instead of the strongest reported baseline | ERC with RoBERTa Large features · IEMOCAP | Accuracy: 69.87 -> 72.46 | Helped |
| Use M3Net's multivariate and multi-frequency propagation instead of the strongest reported baseline | ERC with RoBERTa Large features · MELD | F1: 66.30 -> 67.05 | Helped |
| Add multivariate hypergraph propagation (ablation) | M3Net · IEMOCAP | Accuracy: 70.06 -> 72.46 | Helped |
| Add multi-frequency propagation (ablation) | M3Net · IEMOCAP | Accuracy: 69.87 -> 72.46 | Helped |
| Learn hyperedge weights rather than setting them to 1 (ablation) | M3Net · IEMOCAP | Accuracy: 70.30 -> 72.46 | Helped |
| Learn edge-dependent node weights rather than setting them to 1 (ablation) | M3Net · IEMOCAP | Accuracy: 70.98 -> 72.46 | Helped |
| Learn both hyperedge and edge-dependent node weights rather than setting both to 1 (ablation) | M3Net · IEMOCAP | Accuracy: 70.12 -> 72.46 | Helped |
| Propagate multivariate and multi-frequency information in parallel rather than serially (ablation) | M3Net · IEMOCAP | Accuracy: 68.39 -> 72.46; 69.50 -> 72.46 | Helped |
| Use M3Net's multi-frequency propagation instead of FAGCN's filtering strategy (ablation) | M3Net · IEMOCAP and MELD | Accuracy | Helped |
Closest papers by meaning
- Adaptive Graph Learning for Multimodal Conversational Emotion Detection (AAAI 2024 · similarity 0.91)
- Revisiting Multimodal Emotion Recognition in Conversation from the Perspective of Graph Spectrum (AAAI 2025 · similarity 0.90)
- Dynamic Interactive Bimodal Hypergraph Networks for Emotion Recognition in Conversations (AAAI 2025 · similarity 0.90)
- BIG-FUSION: Brain-Inspired Global-Local Context Fusion Framework for Multimodal Emotion Recognition in Conversations (AAAI 2025 · similarity 0.89)
- Utterance-level Emotion Recognition in Conversation with Conversation-level Supervision (AAAI 2025 · similarity 0.87)
- Beyond Single Emotion: Multi-label Approach to Conversational Emotion Recognition (AAAI 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.