skip to main content


The NSF Public Access Repository (NSF-PAR) system and access will be unavailable from 10:00 PM ET on Friday, December 8 until 2:00 AM ET on Saturday, December 9 due to maintenance. We apologize for the inconvenience.

Title: Source detection on networks using spatial temporal graph convolutional networks
Award ID(s):
1737996 2124313 1737585 2317397
Author(s) / Creator(s):
; ;
Date Published:
Journal Name:
International Conference on Data Science and Advanced Analytics (DSAA)
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Abstract Shared memberships, social statuses, beliefs, and places can facilitate the formation of social ties. Two-mode projections provide a method for transforming two-mode data on individuals’ memberships in such groups into a one-mode network of their possible social ties. In this paper, I explore the opposite process: how social ties can facilitate the formation of groups, and how a two-mode network can be generated from a one-mode network. Drawing on theories of team formation, club joining, and organization recruitment, I propose three models that describe how such groups might emerge from the relationships in a social network. I show that these models can be used to generate two-mode networks that have characteristics commonly observed in empirical two-mode social networks and that they encode features of the one-mode networks from which they were generated. I conclude by discussing these models’ limitations and future directions for theory and methods concerning group formation. 
    more » « less
  2. null (Ed.)
  3. null (Ed.)
    For the past few years, deep learning (DL) robustness (i.e. the ability to maintain the same decision when inputs are subject to perturbations) has become a question of paramount importance, in particular in settings where misclassification can have dramatic consequences. To address this question, authors have proposed different approaches, such as adding regularizers or training using noisy examples. In this paper we introduce a regularizer based on the Laplacian of similarity graphs obtained from the representation of training data at each layer of the DL architecture. This regularizer penalizes large changes (across consecutive layers in the architecture) in the distance between examples of different classes, and as such enforces smooth variations of the class boundaries. We provide theoretical justification for this regularizer and demonstrate its effectiveness to improve robustness on classical supervised learning vision datasets for various types of perturbations. We also show it can be combined with existing methods to increase overall robustness. 
    more » « less
  4. This paper investigates the effect of filtering (or modulating) the functional magnetic resonance imaging (fMRI) time-series on intelligence metrics predicted using dynamic functional connectivity (dFC). Thirteen brain regions that have highest correlation with intelligence are selected and their corresponding time-series are filtered. Using filtered time-series, the modified intelligence metrics are predicted. This experiment investigates whether modulating the time-series of one or two regions of the brain will increase or decrease the fluid ability and fluid intelligence among healthy humans. Two sets of experiments are performed. In the first case, each of the thirteen regions is separately filtered using four different digital filters with passbands: i) 0 - 0.25π, ii) 0.25π - 0.5π, iii) 0.5π - 0.75π, and iv) 0.75π – π, respectively. In the second case, two of the thirteen regions are filtered simultaneously using a low-pass filter of passband 0 - 0.25π. In both cases, the predicted intelligence declined for 45-65% of the subjects after filtering in comparison with the ground truths. In the first case, the low-pass filtering process had the highest predicted intelligence among the four filters. In the second case, it was noticed that the filtering of two regions simultaneously resulted in a higher prediction of intelligence for over 80% of the subjects compared to low-pass filtering of a single region. 
    more » « less
  5. Measuring importance of nodes in a graph is one of the key aspects in graph analysis. Betweenness centrality (BC) measures the amount of influence that a node has over the flow of information in a graph. However, the computation complexity of calculating BC is extremely high with large-scale graphs. This is especially true when analyzing the road networks with millions of nodes and edges. In this study, we propose a deep learning architecture RoadCaps to estimate BC with sub-second latencies. RoadCaps aggregates features from neighbor nodes using Graph Convolutional Networks and estimates the node level BC by mapping low-level concept to high-level information using Capsule Networks. Our empirical benchmarks demonstrates that RoadCaps outperforms base models such as GCN and GCNFCL in both accuracy and robustness. On average, RoadCaps generates a node’s BC value in 7.5 milliseconds. 
    more » « less