AsyReC: A Multimodal Graph-based Framework for Spatio-Temporal Asymmetric Dyadic Relationship Classification

2025-04-07

AI Summary

Addressing three key challenges in real-world social interactions—relational asymmetry, lack of temporal continuity, and insufficient modeling of periodic behavioral patterns—this paper proposes a fine-grained, continuous, and period-aware relational modeling framework. Methodologically: (1) a node-edge dual-attention ternary graph network is designed to explicitly capture relational asymmetry; (2) a video-clip-level temporal learning architecture preserves interaction continuity; and (3) a sinusoidal-cosine projected periodic time encoder is introduced to model rhythmic interaction patterns. By integrating graph neural networks, multimodal signals, and attention mechanisms, the framework achieves state-of-the-art performance on two public benchmarks. Ablation studies demonstrate that both asymmetric relation modeling and periodic time encoding significantly enhance robustness in realistic scenarios.

Technology Category

• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Reasoning under Uncertainty: Relational Probabilistic Models
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

Abstract

Dyadic social relationships, which refer to relationships between two individuals who know each other through repeated interactions (or not), are shaped by shared spatial and temporal experiences. Current computational methods for modeling these relationships face three major challenges: (1) the failure to model asymmetric relationships, e.g., one individual may perceive the other as a friend while the other perceives them as an acquaintance, (2) the disruption of continuous interactions by discrete frame sampling, which segments the temporal continuity of interaction in real-world scenarios, and (3) the limitation to consider periodic behavioral cues, such as rhythmic vocalizations or recurrent gestures, which are crucial for inferring the evolution of dyadic relationships. To address these challenges, we propose AsyReC, a multimodal graph-based framework for asymmetric dyadic relationship classification, with three core innovations: (i) a triplet graph neural network with node-edge dual attention that dynamically weights multimodal cues to capture interaction asymmetries (addressing challenge 1); (ii) a clip-level relationship learning architecture that preserves temporal continuity, enabling fine-grained modeling of real-world interaction dynamics (addressing challenge 2); and (iii) a periodic temporal encoder that projects time indices onto sine/cosine waveforms to model recurrent behavioral patterns (addressing challenge 3). Extensive experiments on two public datasets demonstrate state-of-the-art performance, while ablation studies validate the critical role of asymmetric interaction modeling and periodic temporal encoding in improving the robustness of dyadic relationship classification in real-world scenarios. Our code is publicly available at: https://github.com/tw-repository/AsyReC.

Problem

• Modeling asymmetric dyadic relationships in social interactions
• Preserving temporal continuity in discrete frame-sampled interactions
• Incorporating periodic behavioral cues for relationship evolution

Innovation

• Triplet graph neural network with dual attention
• Clip-level relationship learning for temporal continuity
• Periodic temporal encoder using sine/cosine waveforms