Match!
Kuntal Dey
IBM
Machine learningData miningNatural language processingComputer scienceSocial network
95Publications
8H-index
331Citations
What is this?
Publications 54
Newest
#1Karanbir Singh Chahal (NYU: New York University)H-Index: 1
#2Manraj Singh Grover (IIIT-D: Indraprastha Institute of Information Technology)
Last. Rajiv Ratn Shah (IIIT-D: Indraprastha Institute of Information Technology)H-Index: 11
view all 4 authors...
Abstract Deep learning has led to tremendous advancements in the field of Artificial Intelligence. One caveat, however, is the substantial amount of compute needed to train these deep learning models. Training a benchmark dataset like ImageNet on a single machine with a modern GPU can take up to a week and distributing training on multiple machines has been observed to drastically bring this time down. Recent work has brought down ImageNet training time to as low as 4 min by using a cluster of 2...
3 CitationsSource
Aug 12, 2019 in FSE (Foundations of Software Engineering)
#1Aniya Aggarwal (IBM)H-Index: 1
#2Pranay Lohia (IBM)H-Index: 2
Last. Diptikalyan Saha (IBM)H-Index: 23
view all 5 authors...
Any given AI system cannot be accepted unless its trustworthiness is proven. An important characteristic of a trustworthy AI system is the absence of algorithmic bias. 'Individual discrimination' exists when a given individual different from another only in 'protected attributes' (e.g., age, gender, race, etc.) receives a different decision outcome from a given machine learning (ML) model as compared to the other individual. The current work addresses the problem of detecting the presence of ind...
1 CitationsSource
Fairness is an increasingly important concern as machine learning models are used to support decision making in high-stakes applications such as mortgage lending, hiring, and prison sentencing. This article introduces a new open-source Python toolkit for algorithmic fairness, AI Fairness 360 (AIF360), released under an Apache v2.0 license ( https://github.com/ibm/aif360 ). The main objectives of this toolkit are to help facilitate the transition of fairness research algorithms for use in an indu...
5 CitationsSource
#1Rachel K. E. Bellamy (IBM)H-Index: 23
#2Kuntal Dey (IBM)H-Index: 8
Last. Yunfeng Zhang (IBM)H-Index: 5
view all 17 authors...
Today, machine-learning software is used to help make decisions that affect people's lives. Some people believe that the application of such software results in fairer decisions because, unlike humans, machine-learning software generates models that are not biased. Think again. Machine-learning software is also biased, sometimes in similar ways to humans, often in different ways. While fair model- assisted decision making involves more than the application of unbiased models-consideration of app...
Source
#1Arup BaruahH-Index: 1
Last. Kuntal DeyH-Index: 8
view all 3 authors...
Jan 1, 2019 in NAACL (North American Chapter of the Association for Computational Linguistics)
#1Arup BaruahH-Index: 1
#2Ferdous A. Barbhuiya (IIIT: Indian Institutes of Information Technology)H-Index: 9
Last. Kuntal Dey (IBM)H-Index: 8
view all 3 authors...
1 Citations
#1Kuntal Dey (IBM)H-Index: 8
#2Ritvik Shrivastava (Columbia University)H-Index: 2
Last. Kritika GargH-Index: 1
view all 4 authors...
We perform a first-of-its-kind characterization of topical homophily - familiarity co-occurring with topic-participation similarity of user pairs - by correlating topic participation similarity and degree of familiarity of users on Twitter. We quantify similarity between a user pair by measuring their distribution of participation in topics, wherein topics are defined as clusters of hashtags formed using semantically related user-generated content. We examine the topic participation similarity o...
Source
#1Kuntal Dey (IBM)H-Index: 8
#2Hemank Lamba (CMU: Carnegie Mellon University)H-Index: 8
Last. Saroj Kaushik (IITs: Indian Institutes of Technology)H-Index: 8
view all 5 authors...
Traditional information spread and activation models on social networks, fail to take user interests towards specific content (topics) into account. To this, we propose a predictive topical spreading activation model (TopSPA). Following cues from the well-known spreading activation (SPA) model, we design the TopSPA algorithm to include the affinity of users to given topics. TopSPA utilizes the social connection structures of users, along with their topic affinities, to model the information flow...
Source
#1Kuntal Dey (IBM)H-Index: 8
#2Saroj Kaushik (IITD: Indian Institute of Technology Delhi)H-Index: 8
Last. Ritvik Shrivastava (Columbia University)H-Index: 2
view all 4 authors...
The hashtag recommendation systems on Twitter have largely focused on analyzing the text content of tweets. In this work, we modify the state-of-the-art existing natural language processing (NLP) technique and deeply ingrain socio-temporal techniques into the overall process, to model a novel hashtag recommendation system. The social aspect of the system aims to make use of the hashtags generated by familiar individuals possess, as well as, the hashtags used by the individual at the past (profil...
Source
Deep learning has led to tremendous advancements in the field of Artificial Intelligence. One caveat however is the substantial amount of compute needed to train these deep learning models. Training a benchmark dataset like ImageNet on a single machine with a modern GPU can take upto a week, distributing training on multiple machines has been observed to drastically bring this time down. Recent work has brought down ImageNet training time to a time as low as 4 minutes by using a cluster of 2048 ...
123456