An official website of the United States government
IntroductionBig graphs like social network user interactions and customer rating matrices require significant computing resources to maintain. Data owners are now using public cloud resources for storage and computing elasticity. However, existing solutions do not fully address the privacy and ownership protection needs of the key involved parties: data contributors and the data owner who collects data from contributors. MethodsWe propose a Trusted Execution Environment (TEE) based solution: TEE-Graph for graph spectral analysis of outsourced graphs in the cloud. TEEs are new CPU features that can enable much more efficient confidential computing solutions than traditional software-based cryptographic ones. Our approach has several unique contributions compared to existing confidential graph analysis approaches. (1) It utilizes the unique TEE properties to ensure contributors' new privacy needs, e.g., the right of revocation for shared data. (2) It implements efficient access-pattern protection with a differentially private data encoding method. And (3) it implements TEE-based special analysis algorithms: the Lanczos method and the Nystrom method for efficiently handling big graphs and protecting confidentiality from compromised cloud providers. ResultsThe TEE-Graph approach is much more efficient than software crypto approaches and also immune to access-pattern-based attacks. Compared with the best-known software crypto approach for graph spectral analysis, PrivateGraph, we have seen that TEE-Graph has 103−105times lower computation, storage, and communication costs. Furthermore, the proposed access-pattern protection method incurs only about 10%-25% of the overall computation cost. DiscussionOur experimentation showed that TEE-Graph performs significantly better and has lower costs than typical software approaches. It also addresses the unique ownership and access-pattern issues that other TEE-related graph analytics approaches have not sufficiently studied. The proposed approach can be extended to other graph analytics problems with strong ownership and access-pattern protection.
more »
« less
Graph theory and graph neural network assisted high-throughput crystal structure prediction and screening for energy conversion and storage
Prediction of crystal structures with desirable material properties is a grand challenge in materials research. We deployed graph theory assisted structure searcher and combined with universal machine learning potentials to accelerate the process.
more »
« less
- PAR ID:
- 10527988
- Publisher / Repository:
- RSC
- Date Published:
- Journal Name:
- Journal of Materials Chemistry A
- Volume:
- 12
- Issue:
- 14
- ISSN:
- 2050-7488
- Page Range / eLocation ID:
- 8502 to 8515
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Graph Neural Networks (GNNs) have gained significant attention in recent years due to their ability to learn representations of graph-structured data. Two common methods for training GNNs are mini-batch training and full-graph training. Since these two methods require different training pipelines and systems optimizations, two separate classes of GNN training systems emerged, each tailored for one method. Works that introduce systems belonging to a particular category predominantly compare them with other systems within the same category, offering limited or no comparison with systems from the other category. Some prior work also justifies its focus on one specific training method by arguing that it achieves higher accuracy than the alternative. The literature, however, has incomplete and contradictory evidence in this regard. In this paper, we provide a comprehensive empirical comparison of representative full-graph and mini-batch GNN training systems. We find that the mini-batch training systems consistently converge faster than the full-graph training ones across multiple datasets, GNN models, and system configurations. We also find that minibatch training techniques converge to similar to or often higher accuracy values than full-graph training ones, showing that minibatch sampling is not necessarily detrimental to accuracy. Our work highlights the importance of comparing systems across different classes, using time-to-accuracy rather than epoch time for performance comparison, and selecting appropriate hyperparameters for each training method separately.more » « less
-
Learning high-level representations for graphs is crucial for tasks like node classification, where graph pooling aggregates node features to provide a holistic view that enhances predictive performance. Despite numerous methods that have been proposed in this promising and rapidly developing research field, most efforts to generalize the pooling operation to graphs are primarily performance-driven, with fairness issues largely overlooked: i) the process of graph pooling could exacerbate disparities in distribution among various subgroups; ii) the resultant graph structure augmentation may inadvertently strengthen intra-group connectivity, leading to unintended inter-group isolation. To this end, this paper extends the initial effort on fair graph pooling to the development of fair graph neural networks, while also providing a unified framework to collectively address group and individual graph fairness. Our experimental evaluations on multiple datasets demonstrate that the proposed method not only outperforms state-of-the-art baselines in terms of fairness but also achieves comparable predictive performance.more » « less
-
Abstract Using a mixed methods approach, we explore a relationship between students’ graph reasoning and graph selection via a fully online assessment. Our population includes 673 students enrolled in college algebra, an introductory undergraduate mathematics course, across four U.S. postsecondary institutions. The assessment is accessible on computers, tablets, and mobile phones. There are six items; for each, students are to view a video animation of a dynamic situation (e.g., a toy car moving along a square track), declare their understanding of the situation, select a Cartesian graph to represent a relationship between given attributes in the situation, and enter text to explain their graph choice. To theorize students’ graph reasoning, we draw on Thompson’s theory of quantitative reasoning, which explains students’ conceptions of attributes as being possible to measure. To code students’ written responses, we appeal to Johnson and colleagues’ graph reasoning framework, which distinguishes students’ quantitative reasoning about one or more attributes capable of varying (Covariation, Variation) from students’ reasoning about observable elements in a situation (Motion, Iconic). Quantitizing those qualitative codes, we examine connections between the latent variables of students’ graph reasoning and graph selection. Using structural equation modeling, we report a significant finding: Students’ graph reasoning explains 40% of the variance in their graph selection (standardized regression weight is 0.64,p < 0.001). Furthermore, our results demonstrate that students’ quantitative forms of graph reasoning (i.e., variational and covariational reasoning) influence the accuracy of their graph selection.more » « less
-
Abstract This paper extends the Bakry-Émery criterion relating the Ricci curvature and logarithmic Sobolev inequalities to the noncommutative setting. We obtain easily computable complete modified logarithmic Sobolev inequalities of graph Laplacians and Lindblad operators of the corresponding graph Hörmander systems. We develop the anti-transference principle stating that the matrix-valued modified logarithmic Sobolev inequalities of sub-Laplacian operators on a compact Lie group are equivalent to such inequalities of a family of the transferred Lindblad operators with a uniform lower bound.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1039/d3ta06190f
