Answering Why-questions by Exemplars in Attributed Graphs

Namaki, Mohammad Hossein; Song, Qi; Wu, Yinghui; Yang, Shengqi

doi:10.1145/3299869.3319890

Cited by 18 publications

(5 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, we describe the survey related to constraint reachability techniques [9,11,20,23,42,43] and attributed graph clustering techniques [2,4,6,8,14,16,22,[32][33][34][39][40][41]. We also discuss our important observations derived to solve MCR queries efficiently and effectively.…”

Section: Related Workmentioning

confidence: 99%

“…They developed sampling-based estimation algorithms to find the matching of the spatial path patterns. Namaki et al [14] developed Q-Chase based algorithms to handle unexpected entities and missing entities during pattern matching. The Q-Chase algorithms perform query writing and query optimization using atomic operators and pruning.…”

Section: Constraint Reachability Techniquesmentioning

confidence: 99%

See 1 more Smart Citation

Finding Multidimensional Constraint Reachable Paths for Attributed Graphs

Bhargavi

Rani

Neog

2022

EAI Endorsed Scal Inf Syst

View full text Add to dashboard Cite

A graph acts as a powerful modelling tool to represent complex relationships between objects in the big data era. Given two vertices, vertex and edge constraints, the multidimensional constraint reachable ( MCR) paths problem finds the path between the given vertices that match the user-specified constraints. A significant challenge is to store the graph topology and attribute information while constructing a reachability index. We propose an optimized hashing-based heuristic search technique to address this challenge while solving the multidimensional constraint reachability queries. In the proposed technique, we optimize hashing and recommend an efficient clustering technique based on matrix factorization. We further extend the heuristic search technique to improve the accuracy. We experimentally prove that our proposed techniques are scalable and accurate on real and synthetic datasets. Our proposed extended heuristic search technique is able to achieve an average execution time of 0.17 seconds and 2.55 seconds on MCR true queries with vertex and edge constraints for Robots and Twitter datasets respectively.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Constraint Reachability Techniquesmentioning

confidence: 99%

Finding Multidimensional Constraint Reachable Paths for Attributed Graphs

Bhargavi

Rani

Neog

2022

EAI Endorsed Scal Inf Syst

View full text Add to dashboard Cite

show abstract

“…It can be as coarse-grain as datasets, files, and their dependencies [14] or fine-grain including dependencies between input, intermediate, and output records [20,35,51]. The value of provenance is most exaggerated by the applications that it can support including, but not limited to, explanations [44,65,24]; interactive visualizations [51,50,52,30]; verification and recomputation when data sources are outdated or not reliable [32], debugging [33,36,21]; data integration [22]; auditing and compliance [4]; and security [19,35]. Finally, central to how provenance is utilized across domains is the task of provenance querying, a task complementary to the task of provenance capture.…”

Section: Related Workmentioning

confidence: 99%

Vamsa: Automated Provenance Tracking in Data Science Scripts

Namaki,

Floratou,

Psallidas

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Machine learning (ML) which was initially adopted for search ranking and recommendation systems has firmly moved into the realm of core enterprise operations like sales optimization and preventative healthcare. For such ML applications, often deployed in regulated environments, the standards for user privacy, security, and data governance are substantially higher. This imposes the need for tracking provenance end-to-end, from the data sources used for training ML models to the predictions of the deployed models.In this work, we take a first step towards this direction by introducing the ML provenance tracking problem in the context of data science scripts. The fundamental idea is to automatically identify the relationships between data and ML models and in particular, to track which columns in a dataset have been used to derive the features of a ML model. We discuss the challenges in capturing such provenance information in the context of Python, the most common language used by data scientists. We then, present Vamsa, a modular system that extracts provenance from Python scripts without requiring any changes to the users' code. Using up to 450K real-world data science scripts from Kaggle and publicly available Python notebooks, we verify the effectiveness of Vamsa in terms of coverage, and performance. We also evaluate Vamsa's accuracy on a smaller subset of manually labeled data. Our analysis shows that Vamsa's precision and recall range from 87.5% to 98.3% and its latency is typically in the order of milliseconds for scripts of average size.

show abstract

“…Two recent work GQBE [38] and Exemplar queries [39] are proposed for searching matches that are same as their counterparts from the examples. Moreover, [40], [41] are proposed to pose exemplars characterized by tuple patterns, and identify both query rewrites and their answers close to exemplar. Our approach can be deployed in these QBE methods to extend them by returning more reasonable answers that are semantically similar to the given exemplar queries.…”

Section: Related Workmentioning

confidence: 99%

Semantic Guided and Response Times Bounded Top-k Similarity Search over Knowledge Graphs

Wang¹,

Khan²,

Wu³

et al. 2019

Preprint

View full text Add to dashboard Cite

Recently, graph query is widely adopted for querying knowledge graphs. Given a query graph GQ, graph query finds subgraphs in a knowledge graph G that exactly or approximately match GQ. We face two challenges on graph query over a knowledge graph: (1) the structural gap between GQ and the predefined schema in G causes mismatch with query graph, (2) users cannot view the answers until the graph query terminates, leading to a longer system response time (SRT). In this paper, we propose a semantic guided and response-timebounded graph query to return top-k answers effectively and efficiently. We first leverage a knowledge graph embedding model to build the semantic graph SGQ for each GQ. Then we define the path semantic similarity (pss) over SGQ to evaluate the answer's quality. We propose an A* semantic search on SGQ to find top-k answers with the greatest pss via a heuristic pss estimation. Furthermore, we make an approximate optimization on A* semantic search to allow users to trade off the effectiveness for SRT within a user-specific time bound. Extensive experiments over real datasets confirm the effectiveness and efficiency.

show abstract

Answering Why-questions by Exemplars in Attributed Graphs

Cited by 18 publications

References 30 publications

Finding Multidimensional Constraint Reachable Paths for Attributed Graphs

Finding Multidimensional Constraint Reachable Paths for Attributed Graphs

Vamsa: Automated Provenance Tracking in Data Science Scripts

Semantic Guided and Response Times Bounded Top-k Similarity Search over Knowledge Graphs

Contact Info

Product

Resources

About