Search for: All records

The classic problem of exact subgraph matching returns those subgraphs in a large-scale data graph that are isomorphic to a given query graph, which has gained increasing importance in many real-world applications such as social network analysis, knowledge graph discovery in the Semantic Web, bibliographical network mining, and so on. In this paper, we propose a novel and effective graph neural network (GNN)-based path embedding framework (GNN-PE), which allows efficient exact subgraph matching without introducing false dismissals. Unlike traditional GNN-based graph embeddings that only produce approximate subgraph matching results, in this paper, we carefully devise GNN-based embeddings for paths, such that: if two paths (and 1-hop neighbors of vertices on them) have the subgraph relationship, their corresponding GNN-based embedding vectors will strictly follow the dominance relationship. With such a newly designed property of path dominance embeddings, we are able to propose effective pruning strategies based on path label/dominance embeddings and guarantee no false dismissals for subgraph matching. We build multidimensional indexes over path embedding vectors, and develop an efficient subgraph matching algorithm by traversing indexes over graph partitions in parallel and applying our pruning methods. We also propose a cost-model-based query plan that obtains query paths from the query graph with low query cost. Through extensive experiments, we confirm the efficiency and effectiveness of our proposed GNN-PE approach for exact subgraph matching on both real and synthetic graph data. 

Abstract Geomagnetic storms transfer massive amounts of energy from the sun to geospace. Some of that energy is dissipated in the ionosphere as energetic particles precipitate and transfer their energy to the atmosphere, creating the aurora. We used the Time History of Events and Macroscale Interactions during Substorms (THEMIS) mosaic of all‐sky‐imagers across Canada and Alaska to measure the amount of energy flux deposited into the ionosphere via auroral precipitation during the 2013 March 17 storm. We determined the time‐dependent percent of the total energy flux that is contributed by meso‐scale (<500 km wide) auroral features, discovering they contribute up to 80% during the sudden storm commencement (SSC) and >∼40% throughout the main phase, indicating meso‐scale dynamics are important aspects of a geomagnetic storm. We found that average conductance was higher north of 65° until SYM‐H reached −40 nT. We also found that the median conductance was higher in the post‐midnight sector during the SSC, though localized conductance peaks (sometimes >75 mho) were much higher in the pre‐midnight sector throughout. We related the post‐midnight/pre‐dawn conductance to other recent findings regarding meso‐scale dynamics in the literature. We found sharp conductance peaks and gradients in both time and space related to meso‐scale aurora. Data processing included a new moonlight removal algorithm and cross‐instrument calibration with a meridian scanning photometer and a standard photometer. We compared ASI results to Poker Flat Incoherent Scatter Radar (PFISR) observations, finding energy flux, mean energy, and Hall conductance were highly correlated, moderately correlated, and highly correlated, respectively. 

In many real-world applications such as social network analysis and online marketing/advertising, community detection is a fundamental task to identify communities (subgraphs) in social networks with high structural cohesiveness. While previous works focus on detecting communities alone, they do not consider the collective influences of users in these communities on other user nodes in social networks. Inspired by this, in this paper, we investigate the influence propagation from some seed communities and their influential effects that result in the influenced communities. We propose a novel problem, named Top-L most Influential Community DEtection (TopL-ICDE) over social networks, which aims to retrieve top-L seed communities with the highest influences, having high structural cohesiveness, and containing user-specified query keywords. To efficiently tackle the TopL-ICDE problem, we design effective pruning strategies to filter out false alarms of seed communities and propose an effective index mechanism to facilitate efficient Top-L community retrieval. We develop an efficient TopL-ICDE answering algorithm by traversing the index and applying our proposed pruning strategies. We also formulate and tackle a variant of TopL-ICDE, named diversified top-L most influential community detection (DTopL-ICDE), which returns a set of L diversified communities with the highest diversity score (i.e., collaborative influences by L communities). We prove that DTopL-ICDE is NP-hard, and propose an efficient greedy algorithm with our designed diversity score pruning. Through extensive experiments, we verify the efficiency and effectiveness of our proposed TopL-ICDE and DTopL-ICDE approaches over real/synthetic social networks under various parameter settings. 

Although Federated Learning (FL) enables global model training across clients without compromising their raw data, due to the unevenly distributed data among clients, existing Federated Averaging (FedAvg)-based methods suffer from the problem of low inference performance. Specifically, different data distributions among clients lead to various optimization directions of local models. Aggregating local models usually results in a low-generalized global model, which performs worse on most of the clients. To address the above issue, inspired by the observation from a geometric perspective that a well-generalized solution is located in a flat area rather than a sharp area, we propose a novel and heuristic FL paradigm named FedMR (Federated Model Recombination). The goal of FedMR is to guide the recombined models to be trained towards a flat area. Unlike conventional FedAvg-based methods, in FedMR, the cloud server recombines collected local models by shuffling each layer of them to generate multiple recombined models for local training on clients rather than an aggregated global model. Since the area of the flat area is larger than the sharp area, when local models are located in different areas, recombined models have a higher probability of locating in a flat area. When all recombined models are located in the same flat area, they are optimized towards the same direction. We theoretically analyze the convergence of model recombination. Experimental results show that, compared with state-of-the-art FL methods, FedMR can significantly improve the inference accuracy without exposing the privacy of each client. 

Research shows formative assessments substantially strengthen learning and support summative assessment/evaluation practices. These practices are not widely applied in ATE's professional development (PD) efforts. This study focuses on participant teachers' assessment involvement to increase student learning and enhance outcome evaluations. We surveyed all principal investigators of ATE projects in 2022 who applied assessments in their 2021 PD efforts (N=70). Findings show that a minority of PD efforts apply formative assessment practices to strengthen PD outcomes or meet ATE's evaluation specifications. Assessment practices were most prevalent for summative purposes at the close of PD activity; a large majority assessed teachers' interest and learning in the PD and their intentions to use and teach what was learned on return to their classrooms. A third or less followed up to assess outcomes in teachers' schools. Similarly, thirty percent or less addressed matters of context at any stage of the PD efforts, and a few, 11 percent, followed up to assess the context in the schools. Concomitantly, the findings show where and how attention to formative assessment in the PD learning process can increase teacher involvement in assessment practices, making PD instruction more effective and strengthening outcome evaluations in participant teachers' home classrooms.