DIDER: Discovering Interpretable Dynamically Evolving Relations
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.
Code (0)
등록된 구현이 없습니다.
Tasks
PredictionTrajectory ForecastingSimilar Papers 제목 키워드 기반
MOCHA: Discovering Multi-Order Dynamic Causality in Temporal Point Processes
Discovering complex causal dependencies in temporal point processes (TPPs) is critical for modeling real-world event sequences. Existing methods typically rely on static or first-order causal structures, overlooking the …
Point ProcessesModeling Time-evolving Causality over Data Streams
Given an extensive, semi-infinite collection of multivariate coevolving data sequences (e.g., sensor/web activity streams) whose observations influence each other, how can we discover the time-changing cause-and-effect r…
Learning Differential Operators for Interpretable Time Series Modeling
Modeling sequential patterns from data is at the core of various time series forecasting tasks. Deep learning models have greatly outperformed many traditional models, but these black-box models generally lack explainabi…
Decision MakingMeta-LearningTime SeriesTime Series Analysis+1Neural-based classification rule learning for sequential data
Discovering interpretable patterns for classification of sequential data is of key importance for a variety of fields, ranging from genomics to fraud detection or more generally interpretable decision-making. In this pap…
Binary ClassificationClassificationDecision MakingFraud DetectionLinking Named Entities in Diderot's \textit{Encyclopédie} to Wikidata
Diderot's \textit{Encyclop\'edie} is a reference work from XVIIIth century in Europe that aimed at collecting the knowledge of its era. \textit{Wikipedia} has the same ambition with a much greater scope. However, the lac…
Articles