no code implementations • 2 May 2024 • Sindhu Tipirneni, Ravinarayana Adkathimar, Nurendra Choudhary, Gaurush Hiranandani, Rana Ali Amjad, Vassilis N. Ioannidis, Changhe Yuan, Chandan K. Reddy
Thus, we propose CACTUS (Context-Aware ClusTering with aUgmented triplet losS), a systematic approach that leverages open-source LLMs for efficient and effective supervised clustering of entity subsets, particularly focusing on text-based entities.
no code implementations • 1 Mar 2024 • Nurendra Choudhary, Edward W Huang, Karthik Subbian, Chandan K. Reddy
This lack of interpretability hinders the development and adoption of new techniques in the field.
no code implementations • 15 Jan 2024 • Hamid Ghaderi, Brandon Foreman, Chandan K. Reddy, Vignesh Subbian
Importantly, while certain features varied by age, the core characteristics of TBI manifestations tied to each phenotype remain consistent across diverse populations.
no code implementations • 12 Jan 2024 • Akshita Jha, Vinodkumar Prabhakaran, Remi Denton, Sarah Laszlo, Shachi Dave, Rida Qadri, Chandan K. Reddy, Sunipa Dev
First, we show that stereotypical attributes in ViSAGe are thrice as likely to be present in generated images of corresponding identities as compared to other attributes, and that the offensiveness of these depictions is especially higher for identities from Africa, South America, and South East Asia.
2 code implementations • 3 Oct 2023 • Kazem Meidani, Parshin Shojaee, Chandan K. Reddy, Amir Barati Farimani
To bridge the gap, we introduce SNIP, a Symbolic-Numeric Integrated Pre-training model, which employs contrastive learning between symbolic and numeric domains, enhancing their mutual similarities in the embeddings.
1 code implementation • 19 May 2023 • Akshita Jha, Aida Davani, Chandan K. Reddy, Shachi Dave, Vinodkumar Prabhakaran, Sunipa Dev
Stereotype benchmark datasets are crucial to detect and mitigate social stereotypes about groups of people in NLP models.
1 code implementation • 2 May 2023 • Nurendra Choudhary, Chandan K. Reddy
Reasoning over knowledge graphs (KGs) is a challenging task that requires a deep understanding of the complex relationships between entities and the underlying logic of their relations.
1 code implementation • 23 Mar 2023 • Hamid Ghaderi, Brandon Foreman, Amin Nayebi, Sindhu Tipirneni, Chandan K. Reddy, Vignesh Subbian
Determining clinically relevant physiological states from multivariate time series data with missing values is essential for providing appropriate treatment for acute conditions such as Traumatic Brain Injury (TBI), respiratory failure, and heart failure.
1 code implementation • NeurIPS 2023 • Parshin Shojaee, Kazem Meidani, Amir Barati Farimani, Chandan K. Reddy
Unlike conventional decoding strategies, TPSR enables the integration of non-differentiable feedback, such as fitting accuracy and complexity, as external sources of knowledge into the transformer-based equation generation process.
no code implementations • 27 Feb 2023 • Hamid Ghaderi, Brandon Foreman, Amin Nayebi, Sindhu Tipirneni, Chandan K. Reddy, Vignesh Subbian
To address these challenges, we present a Self-supervised Learning-based Approach to Clustering multivariate Time-series data with missing values (SLAC-Time).
no code implementations • 7 Feb 2023 • Akshita Jha, Adithya Samavedhi, Vineeth Rakesh, Jaideep Chandrashekar, Chandan K. Reddy
Firstly, the performance gain provided by transformer-based models comes at a steep cost - both in terms of the required training time and the resource (memory and energy) consumption.
1 code implementation • 31 Jan 2023 • Parshin Shojaee, Aneesh Jain, Sindhu Tipirneni, Chandan K. Reddy
It's important to note that PPOCoder is a task-agnostic and model-agnostic framework that can be used across different code generation tasks and PLs.
1 code implementation • 13 Aug 2022 • Amin Nayebi, Sindhu Tipirneni, Brandon Foreman, Chandan K. Reddy, Vignesh Subbian
The implemented methods were compared to one another in terms of several XAI characteristics such as understandability, fidelity, and stability.
Explainable artificial intelligence Explainable Artificial Intelligence (XAI) +2
no code implementations • 6 Jul 2022 • Nurendra Choudhary, Nikhil Rao, Karthik Subbian, Chandan K. Reddy
In TESH-GCN, we extract semantic node information, which successively acts as a connection signal to extract relevant nodes' local neighborhood and graph-level metapath features from the sparse adjacency tensor in a reformulated hyperbolic graph convolution layer.
1 code implementation • 16 Jun 2022 • Ming Zhu, Aneesh Jain, Karthik Suresh, Roshan Ravindran, Sindhu Tipirneni, Chandan K. Reddy
To the best of our knowledge, it is the largest parallel dataset for source code both in terms of size and the number of languages.
1 code implementation • 14 Jun 2022 • Chandan K. Reddy, Lluís Màrquez, Fran Valero, Nikhil Rao, Hugo Zaragoza, Sambaran Bandyopadhyay, Arnab Biswas, Anlu Xing, Karthik Subbian
This paper introduces the "Shopping Queries Dataset", a large dataset of difficult Amazon search queries and results, publicly released with the aim of fostering research in improving the quality of search results.
1 code implementation • 10 Jun 2022 • Sindhu Tipirneni, Ming Zhu, Chandan K. Reddy
This paper addresses the problem of code generation, where the goal is to generate target code given source code in a different language or a natural language description.
1 code implementation • 9 Jun 2022 • Mehrdad Khatir, Nurendra Choudhary, Sutanay Choudhury, Khushbu Agarwal, Chandan K. Reddy
Such an approach enables us to propose a hyperbolic normalization layer and to further simplify the entire hyperbolic model to a Euclidean model cascaded with our hyperbolic normalization layer.
no code implementations • 7 Jun 2022 • Nurendra Choudhary, Chandan K. Reddy
However, their adoption in practice remains restricted due to (i) non-scalability on accelerated deep learning hardware, (ii) vanishing gradients due to the closure of hyperbolic space, and (iii) information loss due to frequent mapping between local tangent space and fully hyperbolic space.
2 code implementations • 31 May 2022 • Akshita Jha, Chandan K. Reddy
Pre-trained programming language (PL) models (such as CodeT5, CodeBERT, GraphCodeBERT, etc.,) have the potential to automate software engineering tasks involving code understanding and code generation.
1 code implementation • 10 Apr 2022 • Chang Lu, Chandan K. Reddy, Ping Wang, Dong Nie, Yue Ning
In this work, we propose a Multi-label Time-series GAN (MTGAN) to generate EHR and simultaneously improve the quality of uncommon disease generation.
1 code implementation • NeurIPS 2021 • Nurendra Choudhary, Nikhil Rao, Sumeet Katariya, Karthik Subbian, Chandan K. Reddy
Current approaches employ spatial geometries such as boxes to learn query representations that encompass the answer entities and model the logical operations of projection and intersection.
1 code implementation • 20 Aug 2021 • Akshita Jha, Vineeth Rakesh, Jaideep Chandrashekar, Adithya Samavedhi, Chandan K. Reddy
When handling such long documents, there are three primary challenges: (i) the presence of different contexts for the same word throughout the document, (ii) small sections of contextually similar text between two documents, but dissimilar text in the remaining parts (this defies the basic understanding of "similarity"), and (iii) the coarse nature of a single global similarity measure which fails to capture the heterogeneity of the document content.
no code implementations • 1 Aug 2021 • Ping Wang, Tian Shi, Khushbu Agarwal, Sutanay Choudhury, Chandan K. Reddy
On the other hand, the aspects, entity and context, limit the answers by node-specific information and lead to higher precision and lower recall.
Knowledge Base Question Answering Machine Reading Comprehension
no code implementations • 31 Jul 2021 • Akshita Jha, Bhanukiran Vinzamuri, Chandan K. Reddy
In this paper, we propose a novel method to address two key issues: (a) Can we simultaneously learn fair disentangled representations while ensuring the utility of the learned representation for downstream tasks, and (b)Can we provide theoretical insights into when the proposed approach will be both fair and accurate.
1 code implementation • 29 Jul 2021 • Sindhu Tipirneni, Chandan K. Reddy
In addition, to tackle the problem of limited availability of labeled data (which is typically observed in many healthcare applications), STraTS utilizes self-supervision by leveraging unlabeled data to learn better representations by using time-series forecasting as an auxiliary proxy task.
1 code implementation • 9 Jun 2021 • Chang Lu, Chandan K. Reddy, Yue Ning
Electronic Health Records (EHR) have been heavily used in modern healthcare systems for recording patients' admission information to hospitals.
1 code implementation • 16 May 2021 • Chang Lu, Chandan K. Reddy, Prithwish Chakraborty, Samantha Kleinberg, Yue Ning
Accurate and explainable health event predictions are becoming crucial for healthcare providers to develop care plans for patients.
no code implementations • 5 Apr 2021 • Neal Mangaokar, Jiameng Pu, Parantapa Bhattacharya, Chandan K. Reddy, Bimal Viswanath
The potential for fraudulent claims based on such generated 'fake' medical images is significant, and we demonstrate successful attacks on both X-rays and retinal fundus image modalities.
1 code implementation • 7 Mar 2021 • Ahmadreza Azizi, Ibrahim Asadullah Tahmid, Asim Waheed, Neal Mangaokar, Jiameng Pu, Mobin Javed, Chandan K. Reddy, Bimal Viswanath
T-Miner employs a sequence-to-sequence (seq-2-seq) generative model that probes the suspicious classifier and learns to produce text sequences that are likely to contain the Trojan trigger.
1 code implementation • 23 Dec 2020 • Nurendra Choudhary, Nikhil Rao, Sumeet Katariya, Karthik Subbian, Chandan K. Reddy
Promising approaches to tackle this problem include embedding the KG units (e. g., entities and relations) in a Euclidean space such that the query embedding contains the information relevant to its results.
1 code implementation • 22 Dec 2020 • Amirsina Torfi, Edward A. Fox, Chandan K. Reddy
Deep learning models have demonstrated superior performance in several application problems, such as image classification and speech processing.
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Ming Zhu, Aman Ahuja, Da-Cheng Juan, Wei Wei, Chandan K. Reddy
To this end, we present MASH-QA, a Multiple Answer Spans Healthcare Question Answering dataset from the consumer health domain, where answers may need to be excerpted from multiple, non-consecutive parts of text spanned across a long document.
2 code implementations • 18 Sep 2020 • Tian Shi, Ping Wang, Chandan K. Reddy
In addition, we also propose an Attention-driven Keywords Ranking (AKR) method, which can automatically discover aspect keywords and aspect-level opinion keywords from the review corpus based on the attention weights.
1 code implementation • 18 Sep 2020 • Tian Shi, Liuqing Li, Ping Wang, Chandan K. Reddy
However, recent deep learning-based topic models, specifically aspect-based autoencoder, suffer from several problems, such as extracting noisy aspects and poorly mapping aspects discovered by models to the aspects of interest.
1 code implementation • 22 Jul 2020 • Ping Wang, Khushbu Agarwal, Colby Ham, Sutanay Choudhury, Chandan K. Reddy
Representation learning methods for heterogeneous networks produce a low-dimensional vector embedding for each node that is typically fixed for all tasks involving the node.
1 code implementation • 24 Apr 2020 • Tian Shi, Xuchao Zhang, Ping Wang, Chandan K. Reddy
In this paper, we propose a corpus-level explanation approach, which aims to capture causal relationships between keywords and model predictions via learning the importance of keywords for predicted labels across a training corpus based on attention weights.
1 code implementation • 26 Mar 2020 • Khoa D. Doan, Saurav Manchanda, Fengjiao Wang, Sathiya Keerthi, Avradeep Bhowmik, Chandan K. Reddy
We use the intuition that it is much better to train the GAN generator by minimizing the distributional distance between real and generated images in a small dimensional feature space representing such a manifold than on the original pixel-space.
1 code implementation • 29 Feb 2020 • Khoa D. Doan, Saurav Manchanda, Sarkhan Badirli, Chandan K. Reddy
In this paper, we show that the high sample-complexity requirement often results in sub-optimal retrieval performance of the adversarial hashing methods.
no code implementations • 21 Nov 2019 • Ming Zhu, Busra Celikkaya, Parminder Bhatia, Chandan K. Reddy
This is of significant importance in the biomedical domain, where it could be used to semantically annotate a large volume of clinical records and biomedical literature, to standardized concepts described in an ontology such as Unified Medical Language System (UMLS).
1 code implementation • 28 Jul 2019 • Ping Wang, Tian Shi, Chandan K. Reddy
In this paper, we tackle these challenges by developing a deep learning based TRanslate-Edit Model for Question-to-SQL (TREQS) generation, which adapts the widely used sequence-to-sequence model to directly generate the SQL query for a given question, and further performs the required edits using an attentive-copying mechanism and task-specific look-up tables.
1 code implementation • NAACL 2019 • Tian Shi, Ping Wang, Chandan K. Reddy
Neural abstractive text summarization (NATS) has received a lot of attention in the past few years from both industry and academia.
5 code implementations • 5 Dec 2018 • Tian Shi, Yaser Keneshloo, Naren Ramakrishnan, Chandan K. Reddy
As part of this survey, we also develop an open source library, namely, Neural Abstractive Text Summarizer (NATS) toolkit, for the abstractive text summarization.
1 code implementation • 15 Oct 2018 • Yaser Keneshloo, Naren Ramakrishnan, Chandan K. Reddy
Deep neural networks are data hungry models and thus face difficulties when attempting to train on small text datasets.
3 code implementations • 24 May 2018 • Yaser Keneshloo, Tian Shi, Naren Ramakrishnan, Chandan K. Reddy
In this survey, we consider seq2seq problems from the RL point of view and provide a formulation combining the power of RL methods in decision-making with sequence-to-sequence models that enable remembering long-term memories.
no code implementations • 15 Aug 2017 • Ping Wang, Yan Li, Chandan K. Reddy
We hope that this paper will provide a more thorough understanding of the recent advances in survival analysis and offer some guidelines on applying these approaches to solve new problems that arise in applications with censored data.