Conversational Group Detection with Graph Neural Networks
Conversational Group Detection with Graph Neural Networks
复制标题
DOI：
10.1145/3462244.3479963
复制
发表时间：
2021-10
期刊：
影响因子：
--
通讯作者：
Sydney Thompson;Abhijit Gupta;Anjali W. Gupta;Austin Chen;Marynel Vázquez
中科院分区：
文献类型：
--
作者：
Sydney Thompson;Abhijit Gupta;Anjali W. Gupta;Austin Chen;Marynel Vázquez
我们使用消息传递图神经网络（GNN）结合优势集聚类算法研究了不同社交场景下的会话组检测。我们的方法首先将场景描述为交互图，其中节点编码单个特征，边缘编码成对关系数据。然后，它使用GNN来预测代表两个人在一起互动的可能性的成对亲和力值，并根据这些亲和力计算不重叠的组分配。我们在鸡尾酒会和MatchNMingle数据集上评估了所提出的方法。我们的研究结果表明，当计算组时，使用gnn来利用个体和关系特征是有益的，特别是当每个个体都有更多的特征可用时。
We study conversational group detection in varied social scenes using a message-passing Graph Neural Network (GNN) in combination with the Dominant Sets clustering algorithm. Our approach first describes a scene as an interaction graph, where nodes encode individual features and edges encode pairwise relationship data. Then, it uses a GNN to predict pairwise affinity values that represent the likelihood of two people interacting together, and computes non-overlapping group assignments based on these affinities. We evaluate the proposed approach on the Cocktail Party and MatchNMingle datasets. Our results suggest that using GNNs to leverage both individual and relationship features when computing groups is beneficial, especially when more features are available for each individual.