Learning to Fuse Temporal Proximity Networks: A Case Study in Chimpanzee Social Interactions

TL;DR

This paper presents a method to fuse multiple types of proximity data into a temporal social network model, enabling the detection of meaningful social groups in chimpanzee interactions.

Contribution

It introduces an innovative loss function for optimizing proximity weights in dynamic networks, validated on synthetic and real chimpanzee data.

Findings

Successfully detects stable social groups in chimpanzee networks

Validates approach with synthetic data and real-world observations

Identifies meaningful social cliques consistent with prior research

Abstract

How can we identify groups of primate individuals which could be conjectured to drive social structure? To address this question, one of us has collected a time series of data for social interactions between chimpanzees. Here we use a network representation, leading to the task of combining these data into a time series of a single weighted network per time stamp, where different proximities should be given different weights reflecting their relative importance. We optimize these proximity-type weights in a principled way, using an innovative loss function which rewards structural consistency for consecutive time steps. The approach is empirically validated by carefully designed synthetic data. Using statistical tests, we provide a way of identifying groups of individuals that stay related for a significant length of time. Applying the approach to the chimpanzee data set, we detect cliques in the animal social network time series, which can be validated by real-world intuition from prior research and qualitative observations by chimpanzee experts.