Research map / Graph learning / Knowledge and temporal graphs
Learning Personalised Human Internal Cognition from External Expressive Behaviours for Real Personality Recognition
Xiangyu Kong, Hengde Zhu, Haoqin Sun, Zhihao Guo, Jiayan Gu, Xinyi Ni, Wei Zhang, Shizhe Liu, Siyang Song
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| add FRG-based cognition simulation (ablation) | Ours · NoXI | PCC (avg): 0.110 -> 0.179 | Improved |
| add FRG pre-training (ablation) | Ours · NoXI | PCC (avg): 0.179 -> 0.319 | Improved |
| add FRG pre-training (with end-to-end training) (ablation) | Ours · NoXI | PCC (avg): 0.198 -> 0.324 | Improved |
| use node feature matrices instead of vectors in graph (ablation) | Ours · NoXI | PCC (avg): 0.158 -> 0.254 | Improved |
| add edge feature matrices (ablation) | Ours · NoXI | PCC (avg): 0.262 -> 0.324 | Improved |
| add end-to-end training (ablation) | Ours · NoXI | PCC (avg): 0.319 -> 0.324 | Improved |
| add pre-learned generic cognition Θ to key (vs key only) (ablation) | Ours · NoXI | PCC (avg): 0.198 -> 0.324 | Improved |
| add key to Θ instead of multiplying (ablation) | Ours · NoXI | PCC (avg): 0.223 -> 0.324 | Improved |
| block-level nodes instead of layer-level nodes (ablation) | Ours · NoXI | PCC (avg): 0.274 -> 0.324 | Improved |
| fully connected topology instead of KNN (ablation) | Ours · NoXI | PCC (avg): 0.317 -> 0.324 | Improved |
| fully connected topology instead of KNN (ablation) | Ours · NoXI | MSE (avg): 0.052 -> 0.048 | Improved |
| learned cognition simulation instead of P-NAS architecture search | Ours · NoXI 10-minute clip | inference time: 8.3 days -> 5.29 minutes | Improved |
Closest papers by meaning
- Multimodal Fine-Grained Apparent Personality Trait Recognition: Joint Modeling of Big Five and Questionnaire Item-level Scores (AAAI 2025 · similarity 0.84)
- Data Augmented Graph Neural Networks for Personality Detection (AAAI 2024 · similarity 0.84)
- PersonaX: Multimodal Datasets with LLM-Inferred Behavior Traits (ICLR 2026 · similarity 0.84)
- Pose as a Modality: A Psychology-Inspired Network for Personality Recognition with a New Multimodal Dataset (AAAI 2025 · similarity 0.84)
- Knowledge-Enhanced Hierarchical Heterogeneous Graph for Personality Identification with Limited Training Data (AAAI 2025 · similarity 0.83)
- EmoNet-Face: An Expert-Annotated Benchmark for Synthetic Emotion Recognition (NeurIPS 2025 · similarity 0.83)
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.
