Share This Author
Adversarial Graph Augmentation to Improve Graph Contrastive Learning
A novel principle, termed adversarial-GCL (AD- GCL), is proposed, which enables GNNs to avoid capturing redundant information during the training by optimizing adversarial graph augmentation strategies used in GCL.
Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patterns
This work adopts a generalized concept, node-level assortativity, one that is based at the node level to better represent the diverse patterns and accurately quantify the learnability of GNNs and shows the benefits of adopting this transformation framework for semi-supervised node classification task on a variety of real world graph learning benchmarks.
Towards quantifying the amount of uncollected garbage through image analysis
- Susheel Suresh, Tarun Sharma, K. PrashanthT., V. Subramaniam, D. Sitaram, M. Nirupama
- Computer ScienceICVGIP '16
- 18 December 2016
This paper addresses the problem of quantification of garbage in a dump using a two step approach that builds a mobile application that allows citizens to capture images of garbage and upload them to a server and performs analysis on these images to estimate the amount of garbage using computer vision techniques.
Enforcing Secure Data Sharing in Web Application Development Frameworks Like Django Through Information Flow Control
This paper shows the security flaws that arise by considering different versions of an application package and shows how, these mistakes that arise due to incorrect flow of information can be overcome using the Readers-Writers Flow Model that has the ability to manage the release and subsequent propagation of information.
VoC-DL: Revisiting Voice Of Customer Using Deep Learning
This paper considers higher dimensional extensions to the sentiment concept by incorporating labels like product enquiry, buying intent, seeking help, feedback and pricing query which give us a deeper understanding of the text.
New Software and Platforms - libqif - A Quantitative Information Flow C++ Toolkit Library
A Hybrid Model for Learning Embeddings and Logical Rules Simultaneously from Knowledge Graphs
- Susheel Suresh, Jennifer Neville
- Computer ScienceIEEE International Conference on Data Mining…
- 22 September 2020
This work uses a cross feedback paradigm wherein an embedding model is used to guide the search of a rule mining system to mine rules and infer new facts, which are sampled and further used to refine the embedding models.
CRM Through Customer Online Reviews and Analysis
- Susheel Suresh
Merchants selling products on the Web often ask their customers to review the products that they have purchased and the associated services. As e-commerce is becoming more and more popular, the…
OCTAL: Graph Representation Learning for LTL Model Checking
A novel GRL-based framework OCTAL, is designed to learn the representation of the graph-structured system and specification, which reduces the model checking problem to binary classification in the latent space.