Few Labels are Enough! Semi-Supervised Graph Learning for Social Interaction - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Few Labels are Enough! Semi-Supervised Graph Learning for Social Interaction

Résumé

Endowing machines with social intelligence is a fundamental goal of artificial social intelligence. Dealing with human-centered phenomena requires, however, a considerable amount of manually annotated data, making data annotation a costly and challenging task that hinders the training of supervised learning algorithms. In this study, we apply an approach grounded on Graph Convolutional Network (GCN) to alleviate the annotation burden. As a test bed, we select emergent states analysis with specific reference to the team potency. At first, we build the POTENCY dataset by fusing three datasets on social interaction. Next, we compute a set of multimodal features characterizing the social behavior of the team members and the team as one. Finally, we feed the POTENCY dataset to a semi-supervised GCN, trained on a binary node classification task, with variable amounts of labels. We show that GCN can assign team potency labels to an unlabeled team in the dataset by using only a few labeled examples (i.e., 10% of data), with performances comparable to or higher than those of two baseline algorithms carrying out the same task in a fully supervised way.
Fichier principal
Vignette du fichier
Corbellini_Few_Labels_are_Enough_Semi-Supervised_Graph_Learning_for_Social_Interaction_ICCVW_2023_paper.pdf (587.79 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-04269170 , version 1 (06-11-2023)

Identifiants

  • HAL Id : hal-04269170 , version 1

Citer

Nicola Corbellini, Jhony H. Giraldo, Giovanna Varni, Gualtiero Volpe. Few Labels are Enough! Semi-Supervised Graph Learning for Social Interaction. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, Oct 2023, Paris, France. pp.3060-3068. ⟨hal-04269170⟩
25 Consultations
10 Téléchargements

Partager

Gmail Facebook X LinkedIn More