Effective understanding of dynamically evolving multiagent interactions is
crucial to capturing the underlying behavior of agents in social systems. It is
usually challenging to observe these interactions directly, and therefore
modeling the latent interactions is essential for realizing the complex
behaviors. Recent work on Dynamic Neural Relational Inference (DNRI) captures
explicit inter-agent interactions at every step. However, prediction at every
step results in noisy interactions and lacks intrinsic interpretability without
post-hoc inspection. Moreover, it requires access to ground truth annotations
to analyze the predicted interactions, which are hard to obtain. This paper
introduces DIDER, Discovering Interpretable Dynamically Evolving Relations, a
generic end-to-end interaction modeling framework with intrinsic
interpretability. DIDER discovers an interpretable sequence of inter-agent
interactions by disentangling the task of latent interaction prediction into
sub-interaction prediction and duration estimation. By imposing the consistency
of a sub-interaction type over an extended time duration, the proposed
framework achieves intrinsic interpretability without requiring any post-hoc
inspection. We evaluate DIDER on both synthetic and real-world datasets. The
experimental results demonstrate that modeling disentangled and interpretable
dynamic relations improves performance on trajectory forecasting tasks.

DIDER 是一个通用的端到端交互建模框架，其提供了内在的可解释性，通过将潜在的交互预测任务分解为子交互预测和持续时间估计，利用子交互类型在扩展时间范围内的一致性来实现内在的可解释性，实验结果表明，建模可解释动态关系可以提高轨迹预测任务的性能