Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Learning interaction rules from multi-animal trajectories via augmented behavioral models
Keisuke Fujii, Naoya Takeishi, Kazushi Tsutsui, Emyo Fujioka, Nozomi Nishiumi, Ryooya Tanaka, Mika Fukushiro, Kaoru Ide, Hiroyoshi Kohno, Ken Yoda, Susumu Takahashi, Shizuko Hiryu and 1 more
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 |
|---|---|---|---|
| remove theory-guided regularization L_TG (ablation) | ABM · Boid model | balanced accuracy: 0.683 -> 0.767 | Improved |
| remove theory-guided regularization L_TG (ablation) | ABM · Boid model | AUPRC: 0.638 -> 0.819 | Improved |
| learn navigation function F_N and motion function F_M separately (add F_N) (ablation) | ABM · Boid model | balanced accuracy: 0.542 -> 0.767 | Improved |
| learn navigation function F_N separately (ablation) | ABM · Boid model | AUPRC: 0.385 -> 0.819 | Improved |
| remove both F_N and L_TG (ablation) | ABM · Boid model | balanced accuracy: 0.500 -> 0.767 | Improved |
| add L_TG on top of F_N removal (ablation) | ABM · Boid model | balanced accuracy: 0.500 -> 0.542 | Improved |
| add L_TG regularization (ablation) | ABM · Kuramoto model | balanced accuracy: 0.914 -> 0.902 | No clear effect |
| add L_TG regularization (ablation) | ABM · Kuramoto model | AUROC: 0.972 -> 0.972 | No clear effect |
| ABM versus GVAR baseline | ABM · Boid model | AUPRC: 0.327 -> 0.819 | Improved |
| ABM versus GVAR baseline | ABM · Kuramoto model | AUROC: 0.467 -> 0.972 | Improved |
| ABM versus Local TE baseline | ABM · Boid model | balanced accuracy: 0.634 -> 0.767 | Improved |
| ABM versus eSRU in compute | ABM · Kuramoto model | computation time (s): 162 -> 116 | Improved |
Closest papers by meaning
- The Multi-Agent Behavior Dataset: Mouse Dyadic Social Interactions (NeurIPS 2021 · similarity 0.87)
- Generating Hypotheses of Dynamic Causal Graphs in Neuroscience: Leveraging Generative Factor Models of Observed Time Series (ICML 2025 · similarity 0.85)
- Sim-to-Real Causal Transfer: A Metric Learning Approach to Causally-Aware Interaction Representations (CVPR 2025 · similarity 0.85)
- Flexible inference for animal learning rules using neural networks (NeurIPS 2025 · similarity 0.85)
- UnCLe: Towards Scalable Dynamic Causal Discovery in Non-linear Temporal Systems (NeurIPS 2025 · similarity 0.84)
- Inverse Reinforcement Learning with Switching Rewards and History Dependency for Characterizing Animal Behaviors (ICML 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.
