Search Results for author: Naren Ramakrishnan

Found 40 papers, 23 papers with code

Laying Anchors: Semantically Priming Numerals in Language Modeling

1 code implementation2 Apr 2024 Mandar Sharma, Rutuja Murlidhar Taware, Pravesh Koirala, Nikhil Muralidhar, Naren Ramakrishnan

Off-the-shelf pre-trained language models have become the de facto standard in NLP pipelines for a multitude of downstream tasks.

Language Modelling

Large Multi-Modal Models (LMMs) as Universal Foundation Models for AI-Native Wireless Systems

no code implementations30 Jan 2024 Shengzhe Xu, Christo Kurisummoottil Thomas, Omar Hashash, Nikhil Muralidhar, Walid Saad, Naren Ramakrishnan

Diverging from NLP-based foundation models, the proposed framework promotes the design of large multi-modal models (LMMs) fostered by three key capabilities: 1) processing of multi-modal sensing data, 2) grounding of physical symbol representations in real-world wireless systems using causal reasoning and retrieval-augmented generation (RAG), and 3) enabling instructibility from the wireless environment feedback to facilitate dynamic network adaptation thanks to logical and mathematical reasoning facilitated by neuro-symbolic AI.

Mathematical Reasoning

Learning Non-linguistic Skills without Sacrificing Linguistic Proficiency

1 code implementation14 May 2023 Mandar Sharma, Nikhil Muralidhar, Naren Ramakrishnan

The field of Math-NLP has witnessed significant growth in recent years, motivated by the desire to expand LLM performance to the learning of non-linguistic notions (numerals, and subsequently, arithmetic reasoning).

Arithmetic Reasoning Math

Overcoming Barriers to Skill Injection in Language Modeling: Case Study in Arithmetic

1 code implementation3 Nov 2022 Mandar Sharma, Nikhil Muralidhar, Naren Ramakrishnan

Through their transfer learning abilities, highly-parameterized large pre-trained language models have dominated the NLP landscape for a multitude of downstream language tasks.

Arithmetic Reasoning Language Modelling +2

Detecting Irregular Network Activity with Adversarial Learning and Expert Feedback

1 code implementation1 Oct 2022 Gopikrishna Rathinavel, Nikhil Muralidhar, Timothy O'Shea, Naren Ramakrishnan

Specifically, CAAD employs contrastive learning in an adversarial setup to learn effective representations of normal and anomalous behavior in wireless networks.

Anomaly Detection Contrastive Learning

Memetic algorithms for Spatial Partitioning problems

1 code implementation4 Aug 2022 Subhodip Biswas, Fanglan Chen, Zhiqian Chen, Chang-Tien Lu, Naren Ramakrishnan

However, the search operators employed by these population-based methods are mostly designed for real-parameter continuous optimization problems.

Scrutinizing Shipment Records To Thwart Illegal Timber Trade

no code implementations31 Jul 2022 Debanjan Datta, Sathappan Muthiah, John Simeone, Amelia Meadows, Naren Ramakrishnan

The task of finding such fraudulent activities using trade data, in the absence of ground truth, can be modelled as an unsupervised anomaly detection problem.

Contrastive Learning Unsupervised Anomaly Detection

Innovations in Neural Data-to-text Generation: A Survey

no code implementations25 Jul 2022 Mandar Sharma, Ajay Gogineni, Naren Ramakrishnan

The neural boom that has sparked natural language processing (NLP) research through the last decade has similarly led to significant innovations in data-to-text generation (DTG).

Data-to-Text Generation Fairness

Framing Algorithmic Recourse for Anomaly Detection

no code implementations29 Jun 2022 Debanjan Datta, Feng Chen, Naren Ramakrishnan

We present an approach -- Context preserving Algorithmic Recourse for Anomalies in Tabular data (CARAT), that is effective, scalable, and agnostic to the underlying anomaly detection model.

Anomaly Detection

Sampling-based techniques for designing school boundaries

1 code implementation8 Jun 2022 Subhodip Biswas, Fanglan Chen, Zhiqian Chen, Chang-Tien Lu, Naren Ramakrishnan

Motivated by these recent developments, we develop a set of similar sampling techniques for designing school boundaries based on the flip proposal.

Improving Zero-Shot Event Extraction via Sentence Simplification

no code implementations6 Apr 2022 Sneha Mehta, Huzefa Rangwala, Naren Ramakrishnan

We show how such context simplification can improve the performance of MRC-based event extraction by more than 5% for actor extraction and more than 10% for target extraction.

Event Argument Extraction Extractive Question-Answering +4

Contrastive Graph Convolutional Networks for Hardware Trojan Detection in Third Party IP Cores

no code implementations4 Mar 2022 Nikhil Muralidhar, Abdullah Zubair, Nathanael Weidler, Ryan Gerdes, Naren Ramakrishnan

The availability of wide-ranging third-party intellectual property (3PIP) cores enables integrated circuit (IC) designers to focus on designing high-level features in ASICs/SoCs.

Contrastive Learning

EINNs: Epidemiologically-informed Neural Networks

1 code implementation21 Feb 2022 Alexander Rodríguez, Jiaming Cui, Naren Ramakrishnan, Bijaya Adhikari, B. Aditya Prakash

We introduce EINNs, a framework crafted for epidemic forecasting that builds upon the theoretical grounds provided by mechanistic models as well as the data-driven expressibility afforded by AI models, and their capabilities to ingest heterogeneous information.

Inductive Bias

Deep diffusion-based forecasting of COVID-19 by incorporating network-level mobility information

1 code implementation9 Nov 2021 Padmaksha Roy, Shailik Sarkar, Subhodip Biswas, Fanglan Chen, Zhiqian Chen, Naren Ramakrishnan, Chang-Tien Lu

The Gaussian Mixture Model layer is implemented to consider the multimodal nature of the real-time data while learning from multiple related time series.

Time Series Time Series Analysis

TCube: Domain-Agnostic Neural Time-series Narration

1 code implementation11 Oct 2021 Mandar Sharma, John S. Brownstein, Naren Ramakrishnan

We present TCube (Time-series-to-text), a domain-agnostic neural framework for time-series narration, that couples the representation of essential time-series elements in the form of a dense knowledge graph and the translation of said knowledge graph into rich and fluent narratives through the transfer-learning capabilities of PLMs (Pre-trained Language Models).

Epidemiology Knowledge Graphs +4

Using AntiPatterns to avoid MLOps Mistakes

no code implementations30 Jun 2021 Nikhil Muralidhar, Sathappah Muthiah, Patrick Butler, Manish Jain, Yu Yu, Katy Burne, Weipeng Li, David Jones, Prakash Arunachalam, Hays 'Skip' McCormick, Naren Ramakrishnan

We describe lessons learned from developing and deploying machine learning models at scale across the enterprise in a range of financial analytics applications.

Detecting Anomalies Through Contrast in Heterogeneous Data

no code implementations2 Apr 2021 Debanjan Datta, Sathappan Muthiah, Naren Ramakrishnan

Among other challenges annotations are unavailable for our large-scale trade data with heterogeneous features (categorical and continuous), that can assist in building automated systems to detect fraudulent transactions.

Contrastive Learning Unsupervised Anomaly Detection

Incorporating Expert Guidance in Epidemic Forecasting

no code implementations24 Dec 2020 Alexander Rodríguez, Bijaya Adhikari, Naren Ramakrishnan, B. Aditya Prakash

Forecasting influenza like illnesses (ILI) has rapidly progressed in recent years from an art to a science with a plethora of data-driven methods.

Better call Surrogates: A hybrid Evolutionary Algorithm for Hyperparameter optimization

1 code implementation11 Dec 2020 Subhodip Biswas, Adam D Cobb, Andreea Sistrunk, Naren Ramakrishnan, Brian Jalaian

In this paper, we propose a surrogate-assisted evolutionary algorithm (EA) for hyperparameter optimization of machine learning (ML) models.

Bayesian Optimization BIG-bench Machine Learning +1

STAN: Synthetic Network Traffic Generation with Generative Neural Models

1 code implementation27 Sep 2020 Shengzhe Xu, Manish Marwah, Martin Arlitt, Naren Ramakrishnan

We evaluate the performance of STAN in terms of the quality of data generated, by training it on both a simulated dataset and a real network traffic data set.

Anomaly Detection

Once Upon A Time In Visualization: Understanding the Use of Textual Narratives for Causality

no code implementations6 Sep 2020 Arjun Choudhry, Mandar Sharma, Pramod Chundury, Thomas Kapler, Derek W. S. Gray, Naren Ramakrishnan, Niklas Elmqvist

In this paper, we propose the use of textual narratives as a data-driven storytelling method to augment causality visualization.

Racism is a Virus: Anti-Asian Hate and Counterspeech in Social Media during the COVID-19 Crisis

1 code implementation25 May 2020 Bing He, Caleb Ziems, Sandeep Soni, Naren Ramakrishnan, Diyi Yang, Srijan Kumar

The spread of COVID-19 has sparked racism and hate on social media targeted towards Asian communities.

Low Rank Factorization for Compact Multi-Head Self-Attention

1 code implementation26 Nov 2019 Sneha Mehta, Huzefa Rangwala, Naren Ramakrishnan

Effective representation learning from text has been an active area of research in the fields of NLP and text mining.

General Classification Representation Learning +4

Physics-guided Design and Learning of Neural Networks for Predicting Drag Force on Particle Suspensions in Moving Fluids

1 code implementation6 Nov 2019 Nikhil Muralidhar, Jie Bu, Ze Cao, Long He, Naren Ramakrishnan, Danesh Tafti, Anuj Karpatne

In such situations, it is often useful to rely on machine learning methods to fill in the gap by learning a model of the complex physical process directly from simulation data.

Mitigating Uncertainty in Document Classification

1 code implementation NAACL 2019 Xuchao Zhang, Fanglan Chen, Chang-Tien Lu, Naren Ramakrishnan

The uncertainty measurement of classifiers' predictions is especially important in applications such as medical diagnoses that need to ensure limited human resources can focus on the most uncertain predictions returned by machine learning models.

Document Classification General Classification +2

Patent Citation Dynamics Modeling via Multi-Attention Recurrent Networks

1 code implementation22 May 2019 Taoran Ji, Zhiqian Chen, Nathan Self, Kaiqun Fu, Chang-Tien Lu, Naren Ramakrishnan

For the problem of patent citations, we observe that forecasting a patent's chain of citations benefits from not only the patent's history itself but also from the historical citations of assignees and inventors associated with that patent.

Citation Prediction Point Processes

Neural Abstractive Text Summarization with Sequence-to-Sequence Models

5 code implementations5 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.

Abstractive Text Summarization Language Modelling +1

Deep Transfer Reinforcement Learning for Text Summarization

1 code implementation15 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.

reinforcement-learning Reinforcement Learning (RL) +2

Deep Reinforcement Learning For Sequence to Sequence Models

3 code implementations24 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.

Abstractive Text Summarization Caption Generation +5

Distributed Representation of Subgraphs

no code implementations22 Feb 2017 Bijaya Adhikari, Yao Zhang, Naren Ramakrishnan, B. Aditya Prakash

Motivated by the recent successes of embeddings in natural language processing, researchers have tried to find network embeddings in order to exploit machine learning algorithms for mining tasks like node classification and edge prediction.

Community Detection Node Classification

Distributed Representations of Signed Networks

no code implementations22 Feb 2017 Mohammad Raihanul Islam, B. Aditya Prakash, Naren Ramakrishnan

Recent successes in word embedding and document embedding have motivated researchers to explore similar representations for networks and to use such representations for tasks such as edge prediction, node label prediction, and community detection.

Community Detection Document Embedding +1

Hierarchical Quickest Change Detection via Surrogates

no code implementations31 Mar 2016 Prithwish Chakraborty, Sathappan Muthiah, Ravi Tandon, Naren Ramakrishnan

We propose hierarchical quickest change detection (HQCD), a framework that formalizes the process of incorporating additional correlated sources for early changepoint detection.

Change Detection Time Series +1

Flow of Information in Feed-Forward Deep Neural Networks

no code implementations20 Mar 2016 Pejman Khadivi, Ravi Tandon, Naren Ramakrishnan

Feed-forward deep neural networks have been used extensively in various machine learning applications.

Characterizing Diseases from Unstructured Text: A Vocabulary Driven Word2vec Approach

1 code implementation1 Mar 2016 Saurav Ghosh, Prithwish Chakraborty, Emily Cohn, John S. Brownstein, Naren Ramakrishnan

Traditional disease surveillance can be augmented with a wide variety of real-time sources such as, news and social media.

Word Embeddings

Sparse Estimation of Multivariate Poisson Log-Normal Models from Count Data

no code implementations22 Feb 2016 Hao Wu, Xinwei Deng, Naren Ramakrishnan

Modeling data with multivariate count responses is a challenging problem due to the discrete nature of the responses.


Interactive Storytelling over Document Collections

no code implementations21 Feb 2016 Dipayan Maiti, Mohammad Raihanul Islam, Scotland Leman, Naren Ramakrishnan

Storytelling algorithms aim to 'connect the dots' between disparate documents by linking starting and ending documents through a series of intermediate documents.

Cannot find the paper you are looking for? You can Submit a new open access paper.