Social Processes: Probabilistic Meta-learning for Adaptive Multiparty Interaction Forecasting

TL;DR

This paper introduces Social Process models that leverage probabilistic meta-learning to forecast group social interactions, enabling adaptation to unseen groups and capturing complex multimodal behaviors in social settings.

Contribution

The paper presents a novel meta-learning approach for group-level social interaction forecasting, addressing the gap in modeling complex social dynamics and generalizing to new groups.

Findings

SP models effectively predict future multimodal cues for groups.

Models generalize well to unseen groups in synthetic datasets.

Analysis shows robust latent space representations.

Abstract

Adaptively forecasting human behavior in social settings is an important step toward achieving Artificial General Intelligence. Most existing research in social forecasting has focused either on unfocused interactions, such as pedestrian trajectory prediction, or on monadic and dyadic behavior forecasting. In contrast, social psychology emphasizes the importance of group interactions for understanding complex social dynamics. This creates a gap that we address in this paper: forecasting social interactions at the group (conversation) level. Additionally, it is important for a forecasting model to be able to adapt to groups unseen at train time, as even the same individual behaves differently across different groups. This highlights the need for a forecasting model to explicitly account for each group's unique dynamics. To achieve this, we adopt a meta-learning approach to human behavior forecasting, treating every group as a separate meta-learning task. As a result, our method conditions its predictions on the specific behaviors within the group, leading to generalization to unseen groups. Specifically, we introduce Social Process (SP) models, which predict a distribution over future multimodal cues jointly for all group members based on their preceding low-level multimodal cues, while incorporating other past sequences of the same group's interactions. In this work we also analyze the generalization capabilities of SP models in both their outputs and latent spaces through the use of realistic synthetic datasets.