IDEA

The ML, reasoning, and querying methods highly depend on representation of input data. Users have to find the desired representation for these methods and transform their data to these representations, which are hard and time-consuming. In this project, we build ML, reasoning, and querying systems that work on different representations of the same information. Check out our vision paper for more information.

Publications

• Structural Generalizability: The Case of Similarity Search
  Yodsawalai Chodpathumwan, Arash Termehchy, Aayam Shrestha, Stephen Ramsey, Amy Glen, and Zheng Liu
  The Proceedings of SIGMOD, 2021.
  The full version with proofs
• Logically Scalable and Efficient Relational Learning
  Jose Picado, Arash Termehchy, Alan Fern, and Parisa Ataie
  The VLDB Journal, 2019.
• Variational Databases: Managing Structurally Heterogeneous Databases in Software Product Lines
  Parisa Ataei, Arash Termehchy, and Eric Walkingshaw
  The Proceedings of DBPL, September 2017.
• Schema Independent Relational Learning    [One-slide teaser]    [Slides]
  Jose Picado, Arash Termehchy, Alan Fern, and Parisa Ataie
  The Proceedings of SIGMOD, May 2017.
• Representational Scalability
  Jose Picado
  The Conference on Innovative Data Systems Research (CIDR), abstract, January 2017.
• Schema Independent and Scalable Relational Learning By Castor
  Jose Picado, Parisa Ataie, Arash Termehchy, and Alan Fern
  The Proceedings of the VLDB Endowment (PVLDB), Demonstration track, September 2016.
• Towards Representation Independent Similarity Search Over Graph Databases
  Yodsawalai Chodpathumwan, Amirhossein Aleyasin, Arash Termehchy, and Yizhou Sun
  The Proceedings of CIKM, October 2016.
• Universal-DB: Towards Representation Independent Graph Analytics
  Yodsawalai Chodpathumwan, Amirhossein Aleyasin, Arash Termehchy and Yizhou Sun
  The Proceedings of the VLDB Endowment (PVLDB), Demonstration track, September 2015.
• Towards Schema Independent Relational Learning
  Jose Picado, Arash Termehchy, and Alan Fern
  The NIPS Workshop on Machine Learning Systems, December 2015.
• Schema Independent Relational Learning
  Jose Picado, Arash Termehchy, and Alan Fern
  Technical Report:arXiv:1508.03846, August 2015.
• Representation Independent Similarity and Proximity Search
  Yodsawalai Chodpathumwan, Amirhossein Aleyasin, Arash Termehchy, and Yizhou Sun
  Technical Report:arXiv:1508.03763, August 2015.
• Representation Independent Analytics Over Structured Data
  Yodswalai Chodpathumwan, Jose Picado, Arash Termehchy, Alan Fern, and Yizhou Sun
  Technical Report: arXiv:1409.2553, August 2014.
• Schema Independence of Relational Learning Algorithms
  Jose Picado, Arash Termehchy, and Alan Fern
  The SIGMOD Workshop on Big Uncertain Data (BUDA), June 2014.
• Toward Representation Independent Similarity Search Over Graphs
  Yodswalai Chodpathumwan, Arash Termehchy, Yizhou Sun, Amirhossein Aleyasin, and Jose Picado
  The SIGMOD Workshop on Graph Data Management Experiences and Systems (GRADES), June 2014.
• Schema Independent Query Interfaces
  Arash Termehchy, Marianne Winslett, Yodswalai Chodpathumwan, and Austin Gibbons
  The IEEE Transactions on Knowledge and Data Engineering (TKDE), Special Issue on the Best Papers of ICDE 2011, July 2012.
• How Schema Independent are Schema Free Query Interfaces?    [Teaser Slide]
  Arash Termehchy, Marianne Winslett, and Yodsawalai Chodpathumwan
  The Proceedings of IEEE International Conference on Data Engineering (ICDE), April 2011,
  Best Student Paper Award; Bests of Conference Selection .

People

• Arash Termehchy
• Jose Picado
• Yodsawalai Chodpathumwan
• Sudhanshu Shobhakant Pathak