Recent Posts

More Posts

, , , , ,

After waiting what seemed like an eternity (it was just 2 days due to delayed notifications), we got acceptance notifications for both of our submissions. Work led by wonderful Ph.D. students, Vinayak Gupta and Shubham Gupta!!

CONTINUE READING

Last updated on

Garima Gaur, my second Ph.D. student, advised jointly with Arnab Bhattacharya at IITK, successfully defended her thesis titled Provenance-Aware Computation and Maintenance of Graph Query Results under Dynamic Knowledge Graphs. Congratulations, Dr. Gaur!

CONTINUE READING

Despite its importance in many applications, anomaly detection using one-class classification techniques, is notorious for its inability to scale to large features and datasets. We offer FROCC family of one-class classification techniques that are super-fast (12x fast) and accurate (2 pp better than closest deep learning based method). Oh…it scales to millions of dimensions and training datasets easily!

CONTINUE READING

On Summer/Winter Internship Requests

I am NOT offering any short-term projects for internships and I do not have the bandwidth to respond to requests about summer or winter internships. If you are interested in working with me, I recommend you apply for a short-term employment in one of my projects, or join the B.Tech./M.Tech./Ph.D. programs in IIT-Delhi.

Calendar

Please make an appointment based on my availability below

Working Hours: 9:30AM - 12:30PM; 2:00PM - 5:30PM

Recent Publications

More Publications

. Evaluating Cross-modal Generative Models using Retrieval Task (to appear, short-paper). Proc. of the 46th Intl. ACM SIGIR Conf. on Research and Development in Information Retrieval (SIGIR), 2023.

. GRAFENNE: Continual learning on Graphs with Heterogeneous and Dynamic Feature Sets (to appear). Proc. of the 40th International Conference on Machine Learning (ICML), 2023.

. Counterfactual Sentence Generation with Plug-and-Play Perturbation. Proc. of the 1st IEEE Conference on Secure and Trustworthy Machine Learning (IEEE SaTML), 2023.

Preprint

. DetAIL : A Tool to Automatically Detect and Analyze Drift In Language. Proc. of the 35th Conference on Innovative Applications of Artificial Intelligence (AAAI/IAAI), 2023.

Preprint

. LCM: A Surprisingly Effective Framework for Supervised Cross-modal Retrieval. Proc. of the ACM India Joint International Conference on Data Sciences and Management of Data (CoDS-COMAD) 2022 (10th ACM iKDD CoDS and 28th COMAD), 2023.

PDF

Courses

COL 362/632 - Introduction to Database Management Systems (2022-23 Sem 2)

COL 865 - Spl Topics in Computer Applications (2022-23 Sem 1)

Focus on Tabular and Multimodal Data

COL 100 - Introduction to Computer Science (2021-22 Sem 2)

Introduction to CS with Programming in Python

COL 764 - Information Retrieval and Web Search (2021-22 Sem 1)

Understand and implement large-scale search systems effectively and efficiently

COL 873 - Spl Topics in NLP (2020-21 Sem 2)

Advanced Information Retrieval

COL 764 - Information Retrieval and Web Search (2020-21 Sem 1)

Understand and implement large-scale text search systems effectively and efficiently

COL 106 - Datastructures and Algorithms (2019-20 Sem 2)

Datastructures and algorithms using Java.

COL 864 - Spl Topics in AI (2019-20 Sem 1)

Focus on Information Retrieval

COV 888 - Spl. Module in Database Systems (2018-19 Sem 2)

Focus on Knowledge Graph Management and IR

COL 864 - Spl Topics in AI (2018-19 Sem 1)

Focus on Information Retrieval

Projects

*

Multimodel-Multimodal Indexing (2020-- )

Scalable Multi-modal Indexing in Multi-model DBs

IBM-IITD AI Horizons Network (2019-- )

Neuro-Symbolic Information Systems

Social Media Analysis (2018-2021)

Building Platforms for Privacy-preserving and Aggregated Analysis of Media

Students

more

Current

Ph.D.

M.S(Research)

  • Harsh Pandey (IITD) – jointly with Amitabha Bagchi
  • Sai Kandregula (IITD) – jointly with Sayan Ranu
  • Shivangi Bithel (IITD)
  • Prachi (IITD)

M.Tech./Dual

  • Rohan Debbarma (IITD) & Pratik Prawar (IITD) - Legal Informatics – jointly with Abhijnan Chakraborty
  • Nishant Kumar (IITD) & Prateek Chaudhary (IITD) - Word Embeddings

Contact