Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- short-paperJune 2024
User-friendly, Interactive, and Configurable Explanations for Graph Neural Networks with Graph Views
SIGMOD/PODS '24: Companion of the 2024 International Conference on Management of DataJune 2024, Pages 512–515https://doi.org/10.1145/3626246.3654735Explaining the behavior of graph neural networks (GNNs) has become critical due to their "black-box'' nature, especially in the context of analytical tasks such as graph classification. Current approaches are limited to providing explanations for ...
- research-articleMarch 2024
View-based Explanations for Graph Neural Networks
Proceedings of the ACM on Management of Data (PACMMOD), Volume 2, Issue 1Article No.: 40, Pages 1–27https://doi.org/10.1145/3639295Generating explanations for graph neural networks (GNNs) has been studied to understand their behaviors in analytical tasks such as graph classification. Existing approaches aim to understand the overall results of GNNs rather than providing explanations ...
- research-articleOctober 2023
Selecting Top-k Data Science Models by Example Dataset
- Mengying Wang,
- Sheng Guan,
- Hanchao Ma,
- Yiyang Bian,
- Haolai Che,
- Abhishek Daundkar,
- Alp Sehirlioglu,
- Yinghui Wu
CIKM '23: Proceedings of the 32nd ACM International Conference on Information and Knowledge ManagementOctober 2023, Pages 2686–2695https://doi.org/10.1145/3583780.3615051Data analytical pipelines routinely involve various domain-specific data science models. Such models require expensive manual or training effort and often incur expensive validation costs (e.g., via scientific simulation analysis). Meanwhile, high-value ...
- short-paperJune 2023
Demonstration of Geyser: Provenance Extraction and Applications over Data Science Scripts
- Fotis Psallidas,
- Megan Eileen Leszczynski,
- Mohammad Hossein Namaki,
- Avrilia Floratou,
- Ashvin Agrawal,
- Konstantinos Karanasos,
- Subru Krishnan,
- Pavle Subotic,
- Markus Weimer,
- Yinghui Wu,
- Yiwen Zhu
SIGMOD '23: Companion of the 2023 International Conference on Management of DataJune 2023, Pages 123–126https://doi.org/10.1145/3555041.3589717As enterprises have started developing and deploying complicated data science workloads at scale, the need for mechanisms that enable enterprise-grade data science (e.g., compliance or auditing) has become more pronounced. In this paper, we present ...
- research-articleMay 2023
Spatio-Temporal Denoising Graph Autoencoders with Data Augmentation for Photovoltaic Data Imputation
- Yangxin Fan,
- Xuanji Yu,
- Raymond Wieser,
- David Meakin,
- Avishai Shaton,
- Jean-Nicolas Jaubert,
- Robert Flottemesch,
- Michael Howell,
- Jennifer Braid,
- Laura Bruckman,
- Roger French,
- Yinghui Wu
Proceedings of the ACM on Management of Data (PACMMOD), Volume 1, Issue 1Article No.: 50, Pages 1–19https://doi.org/10.1145/3588730The integration of the global Photovoltaic (PV) market with real time data-loggers has enabled large scale PV data analytical pipelines for power forecasting and reliability assessment of PV fleets. Nevertheless, the performance of PV data analysis ...
-
- short-paperOctober 2022
CRUX: Crowdsourced Materials Science Resource and Workflow Exploration
CIKM '22: Proceedings of the 31st ACM International Conference on Information & Knowledge ManagementOctober 2022, Pages 5014–5018https://doi.org/10.1145/3511808.3557194Modern multidisciplinary materials science routinely processes scientific workflows that integrate different data resources (e.g., X-ray data, scripts, analytical results). Most of such data resources are isolated in research labs, created ad-hocly, and ...
- short-paperOctober 2022
System-Auditing, Data Analysis and Characteristics of Cyber Attacks for Big Data Systems
- Liangyi Huang,
- Sophia Hall,
- Fei Shao,
- Arafath Nihar,
- Vipin Chaudhary,
- Yinghui Wu,
- Roger French,
- Xusheng Xiao
CIKM '22: Proceedings of the 31st ACM International Conference on Information & Knowledge ManagementOctober 2022, Pages 4872–4876https://doi.org/10.1145/3511808.3557185Using big data, distributed computing systems such as Apache Hadoop requires processing massive amount of data to support business and research applications. Thus, it is critical to ensure the cyber security of such systems. To better defend from ...
- research-articleOctober 2022
Answering Why-Questions for Subgraph Queries
IEEE Transactions on Knowledge and Data Engineering (IEEECS_TKDE), Volume 34, Issue 10Oct. 2022, Pages 4636–4649https://doi.org/10.1109/TKDE.2020.3046436Subgraph queries are routinely used to search for entities in richly attributed graphs e.g., social networks and knowledge graphs. With little knowledge of underlying data, users often need to rewrite queries multiple times to reach desirable answers. Why-...
- research-articleFebruary 2022
Diversified Subgraph Query Generation with Group Fairness
WSDM '22: Proceedings of the Fifteenth ACM International Conference on Web Search and Data MiningFebruary 2022, Pages 686–694https://doi.org/10.1145/3488560.3498525This paper investigates the problem of subgraph query generation with output that satisfies both diversity and fairness constraints. Given a set of groups with associated cardinality requirements, it is to compute subgraph queries with diversified ...
- research-articleJuly 2021
GEDet: detecting erroneous nodes with a few examples
Proceedings of the VLDB Endowment (PVLDB), Volume 14, Issue 12Pages 2875–2878https://doi.org/10.14778/3476311.3476367Detecting nodes with erroneous values in real-world graphs remains challenging due to the lack of examples and various error scenarios. We demonstrate GEDet, an error detection engine that can detect erroneous nodes in graphs with a few examples. The ...
- short-paperJune 2021
GRIP: Constraint-based Explanation of Missing Answers for Graph Queries
SIGMOD '21: Proceedings of the 2021 International Conference on Management of DataJune 2021, Pages 2779–2783https://doi.org/10.1145/3448016.3452758A useful feature in graph query engines is to clarify "Why certain entities (nodes, attribute values or edges) are missing" in query answers. This task is even more challenging when the relevant data is already missing in the underlying data source. ...
- research-articleAugust 2020
Vamsa: Automated Provenance Tracking in Data Science Scripts
- Mohammad Hossein Namaki,
- Avrilia Floratou,
- Fotis Psallidas,
- Subru Krishnan,
- Ashvin Agrawal,
- Yinghui Wu,
- Yiwen Zhu,
- Markus Weimer
KDD '20: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data MiningAugust 2020, Pages 1542–1551https://doi.org/10.1145/3394486.3403205There has recently been a lot of ongoing research in the areas of fairness, bias and explainability of machine learning (ML) models due to the self-evident or regulatory requirements of various ML applications. We make the following observation: All of ...
- research-articleJuly 2019
Attribute-Driven Backbone Discovery
KDD '19: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data MiningJuly 2019, Pages 187–195https://doi.org/10.1145/3292500.3330934Backbones refer to critical tree structures that span a set of nodes of interests in networks. This paper introduces a novel class of attributed backbones and detection algorithms in richly attributed networks. Unlike conventional models, attributed ...
- research-articleJune 2019
NAVIGATE: Explainable Visual Graph Exploration by Examples
SIGMOD '19: Proceedings of the 2019 International Conference on Management of DataJune 2019, Pages 1965–1968https://doi.org/10.1145/3299869.3320245We demonstrate NAVIGATE, an explai\underlineNA ble query engine for \underlineVI sual \underlineG r\underlineA ph explora\underlineT ion by \underlineE xamples. NAVIGATE interleavesquery rewriting and query answering to help users (1) search graphs \...
- research-articleJune 2019
Answering Why-questions by Exemplars in Attributed Graphs
SIGMOD '19: Proceedings of the 2019 International Conference on Management of DataJune 2019, Pages 1481–1498https://doi.org/10.1145/3299869.3319890This paper studies the problem of \em answering Why-questions for graph pattern queries. Given a query Q, its answers $Q(G)$ in a graph G, and an exemplar $\E$ that describes desired answers, it aims to compute a query rewrite $Q'$, such that $Q'(G)$ ...
- research-articleJune 2019
Ontology-based entity matching in attributed graphs
Proceedings of the VLDB Endowment (PVLDB), Volume 12, Issue 10Pages 1195–1207https://doi.org/10.14778/3339490.3339501Keys for graphs incorporate the topology and value constraints needed to uniquely identify entities in a graph. They have been studied to support object identification, knowledge fusion, and social network reconciliation. Existing key constraints ...
- research-articleMay 2019
Discovering Patterns for Fact Checking in Knowledge Graphs
Journal of Data and Information Quality (JDIQ), Volume 11, Issue 3Article No.: 13, Pages 1–27https://doi.org/10.1145/3286488This article presents a new framework that incorporates graph patterns to support fact checking in knowledge graphs. Our method discovers discriminant graph patterns to construct classifiers for fact prediction. First, we propose a class of graph fact ...
- research-articleOctober 2018
TGNet: Learning to Rank Nodes in Temporal Graphs
CIKM '18: Proceedings of the 27th ACM International Conference on Information and Knowledge ManagementOctober 2018, Pages 97–106https://doi.org/10.1145/3269206.3271698Node ranking in temporal networks are often impacted by heterogeneous context from node content, temporal, and structural dimensions. This paper introduces TGNet , a deep learning framework for node ranking in heterogeneous temporal graphs. TGNet ...
- research-articleSeptember 2018