publications | Aditya Chetan

2024

NeurReps
Distance Learner: Incorporating Manifold Prior to Model Training

Aditya Chetan, and Nipun Kwatra

In Proceedings of the 2nd NeurIPS Workshop on Symmetry and Geometry in Neural Representations, 2024

Abs Bib HTML PDF

The manifold hypothesis (real-world data concentrates near low-dimensional manifolds) is suggested as the principle behind the effectiveness of machine learning algorithms in very high-dimensional problems that are common in domains such as vision and speech. Multiple methods have been proposed to explicitly incorporate the manifold hypothesis as a prior in modern Deep Neural Networks (DNNs), with varying success. In this paper, we propose a new method, Distance Learner, to incorporate this prior for DNN-based classifiers. Distance Learner is trained to predict the distance of a point from the underlying manifold of each class, rather than the class label. For classification, Distance Learner then chooses the class corresponding to the closest predicted class manifold. Distance Learner can also identify points as being out of distribution (belonging to neither class), if the distance to the closest manifold is higher than a threshold. We evaluate our method on multiple synthetic datasets and show that Distance Learner learns much more meaningful classification boundaries compared to a standard classifier. We also evaluate our method on the task of adversarial robustness and find that it not only outperforms standard classifiers by a large margin but also performs at par with classifiers trained via well-accepted standard adversarial training.
@inproceedings{pmlr-v228-chetan24a, title = {Distance Learner: Incorporating Manifold Prior to Model Training}, author = {Chetan, Aditya and Kwatra, Nipun}, booktitle = {Proceedings of the 2nd NeurIPS Workshop on Symmetry and Geometry in Neural Representations}, pages = {366--387}, year = {2024}, editor = {Sanborn, Sophia and Shewmake, Christian and Azeglio, Simone and Miolane, Nina}, volume = {228}, series = {Proceedings of Machine Learning Research}, publisher = {PMLR}, }

2023

Preprint

Accurate Differential Operators for Hybrid Neural Fields

Aditya Chetan, Guandao Yang, Zichen Wang, Steve Marschner, and Bharath Hariharan

2023

@misc{chetan2023accurate,
  title = {Accurate Differential Operators for Hybrid Neural Fields},
  author = {Chetan, Aditya and Yang, Guandao and Wang, Zichen and Marschner, Steve and Hariharan, Bharath},
  year = {2023},
  eprint = {2312.05984},
  archiveprefix = {arXiv},
  primaryclass = {cs.CV},
}

2020

ACM TIST
Analyzing and Detecting Collusive Users Involved in Blackmarket Retweeting Activities

Udit Arora, Hridoy Sankar Dutta, Brihi Joshi, Aditya Chetan, and Tanmoy Chakraborty

ACM Trans. Intell. Syst. Technol., Apr 2020

Abs Bib HTML

With the rise in popularity of social media platforms like Twitter, having higher influence on these platforms has a greater value attached to it, since it has the power to influence many decisions in the form of brand promotions and shaping opinions. However, blackmarket services that allow users to inorganically gain influence are a threat to the credibility of these social networking platforms. Twitter users can gain inorganic appraisals in the form of likes, retweets, and follows through these blackmarket services either by paying for them or by joining syndicates wherein they gain such appraisals by providing similar appraisals to other users. These customers tend to exhibit a mix of organic and inorganic retweeting behavior, making it tougher to detect them.In this article, we investigate these blackmarket customers engaged in collusive retweeting activities. We collect and annotate a novel dataset containing various types of information about blackmarket customers and use these sources of information to construct multiple user representations. We adopt Weighted Generalized Canonical Correlation Analysis (WGCCA) to combine these individual representations to derive user embeddings that allow us to effectively classify users as: genuine users, bots, promotional customers, and normal customers. Our method significantly outperforms state-of-the-art approaches (32.95% better macro F1-score than the best baseline).
@article{collusionTIST, author = {Arora, Udit and Dutta, Hridoy Sankar and Joshi, Brihi and Chetan, Aditya and Chakraborty, Tanmoy}, title = {Analyzing and Detecting Collusive Users Involved in Blackmarket Retweeting Activities}, year = {2020}, issue_date = {June 2020}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, volume = {11}, number = {3}, issn = {2157-6904}, url = {https://doi.org/10.1145/3380537}, doi = {10.1145/3380537}, journal = {ACM Trans. Intell. Syst. Technol.}, month = apr, articleno = {35}, numpages = {24}, keywords = {OSNs, multiview learning, collusion, blackmarket, Twitter, Retweeters} }

NLP4MusA

Did You “Read” the Next Episode? Using Textual Cues for Predicting Podcast Popularity

Brihi Joshi, Shravika Mittal, and Aditya Chetan

In Proceedings of the 1st Workshop on NLP for Music and Audio (NLP4MusA), Oct 2020

Bib HTML

@inproceedings{joshi-etal-2020-read,
  title = {Did You {``}Read{''} the Next Episode? Using Textual Cues for Predicting Podcast Popularity},
  author = {Joshi, Brihi and Mittal, Shravika and Chetan, Aditya},
  booktitle = {Proceedings of the 1st Workshop on NLP for Music and Audio (NLP4MusA)},
  month = oct,
  year = {2020},
  address = {Online},
  publisher = {Association for Computational Linguistics},
  url = {https://aclanthology.org/2020.nlp4musa-1.3},
  pages = {13--17}
}

2019

WSDM
CoReRank: Ranking to Detect Users Involved in Blackmarket-Based Collusive Retweeting Activities

Aditya Chetan, Brihi Joshi, Hridoy Sankar Dutta, and Tanmoy Chakraborty

In Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining, Oct 2019

Abs Bib HTML

Twitter’s popularity has fostered the emergence of various illegal user activities - one such activity is to artificially bolster visibility of tweets by gaining large number of retweets within a short time span. The natural way to gain visibility is time-consuming. Therefore, users who want their tweets to get quick visibility try to explore shortcuts - one such shortcut is to approach the blackmarket services, and gain retweets for their own tweets by retweeting other customers’ tweets. Thus the users intrinsically become a part of a collusive ecosystem controlled by these services. In this paper, we propose CoReRank, an unsupervised framework to detect collusive users (who are involved in producing artificial retweets), and suspicious tweets (which are submitted to the blackmarket services) simultaneously. CoReRank leverages the retweeting (or quoting) patterns of users, and measures two scores - the ’credibility’ of a user and the ’merit’ of a tweet. We propose a set of axioms to derive the interdependency between these two scores, and update them in a recursive manner. The formulation is further extended to handle the cold start problem. CoReRank is guaranteed to converge in a finite number of iterations and has linear time complexity. We also propose a semi-supervised version of CoReRank (called CoReRank+) which leverages a partial ground-truth labeling of users and tweets. Extensive experiments are conducted to show the superiority of CoReRank compared to six baselines on a novel dataset we collected and annotated. CoReRank beats the best unsupervised baseline method by 269% (20%) (relative) average precision and 300% (22.22%) (relative) average recall in detecting collusive (genuine) users. CoReRank+ beats the best supervised baseline method by 33.18% AUC. CoReRank also detects suspicious tweets with 0.85 (0.60) average precision (recall). To our knowledge, CoReRank is the first unsupervised method to detect collusive users and suspicious tweets simultaneously with theoretical guarantees.
@inproceedings{CoReRank, author = {Chetan, Aditya and Joshi, Brihi and Dutta, Hridoy Sankar and Chakraborty, Tanmoy}, title = {CoReRank: Ranking to Detect Users Involved in Blackmarket-Based Collusive Retweeting Activities}, year = {2019}, isbn = {9781450359405}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, url = {https://doi.org/10.1145/3289600.3291010}, doi = {10.1145/3289600.3291010}, booktitle = {Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining}, pages = {330–338}, numpages = {9}, keywords = {online social networks, twitter, collusion, retweets, blackmarket}, location = {Melbourne VIC, Australia}, series = {WSDM '19}, }

2018

ASONAM

Retweet Us, We will Retweet You: Spotting Collusive Retweeters Involved in Blackmarket Services

Hridoy Sankar Dutta, Aditya Chetan, Brihi Joshi, and Tanmoy Chakraborty

In 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), Oct 2018

Bib HTML

@inproceedings{score,
  author = {Dutta, Hridoy Sankar and Chetan, Aditya and Joshi, Brihi and Chakraborty, Tanmoy},
  booktitle = {2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM)},
  title = {Retweet Us, We will Retweet You: Spotting Collusive Retweeters Involved in Blackmarket Services},
  year = {2018},
  volume = {},
  number = {},
  pages = {242-249},
  doi = {10.1109/ASONAM.2018.8508801},
}

Preprint

Generating Clues for Gender based Occupation De-biasing in Text

Nishtha Madaan, Gautam Singh, Sameep Mehta, Aditya Chetan, and Brihi Joshi

CoRR, Oct 2018

Bib HTML

@article{occupationdebias,
  author = {Madaan, Nishtha and Singh, Gautam and Mehta, Sameep and Chetan, Aditya and Joshi, Brihi},
  title = {Generating Clues for Gender based Occupation De-biasing in Text},
  journal = {CoRR},
  volume = {abs/1804.03839},
  year = {2018},
  eprinttype = {arXiv},
  eprint = {1804.03839},
  timestamp = {Mon, 13 Aug 2018 16:46:32 +0200},
  biburl = {https://dblp.org/rec/journals/corr/abs-1804-03839.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org},
}