no code implementations • 30 Jan 2024 • Lei Xu, Sarah Alnegheimish, Laure Berti-Equille, Alfredo Cuesta-Infante, Kalyan Veeramachaneni
Experimental results on 4 datasets and BERT and distilBERT classifiers show that SP-Defense improves \r{ho} by 14. 6% and 13. 9% and decreases the attack success rate of SP-Attack by 30. 4% and 21. 2% on two classifiers respectively, and decreases the attack success rate of existing attack methods that involve multiple-word perturbations.
no code implementations • 20 Dec 2023 • Alexandra Zytek, Wei-En Wang, Dongyu Liu, Laure Berti-Equille, Kalyan Veeramachaneni
Users in many domains use machine learning (ML) predictions to help them make decisions.
no code implementations • 5 Dec 2023 • Alexandra Zytek, Wei-En Wang, Sofia Koukoura, Kalyan Veeramachaneni
Through the applications of our lessons to this task, we hope to demonstrate the potential real-world impact of usable ML in the renewable energy domain.
1 code implementation • 26 Oct 2023 • Sarah Alnegheimish, Laure Berti-Equille, Kalyan Veeramachaneni
The framework provides universal abstractions to represent models, extensibility to add new pipelines and datasets, hyperparameter standardization, pipeline verification, and frequent releases with published benchmarks.
3 code implementations • 27 Dec 2022 • Lawrence Wong, Dongyu Liu, Laure Berti-Equille, Sarah Alnegheimish, Kalyan Veeramachaneni
We then propose AER (Auto-encoder with Regression), a joint model that combines a vanilla auto-encoder and an LSTM regressor to incorporate the successes and address the limitations of each method.
1 code implementation • 28 Jul 2022 • Kevin Zhang, Neha Patki, Kalyan Veeramachaneni
After building the Sequential SDV, we used it to generate synthetic data and compared its quality against an existing, non-sequential generative adversarial network based model called CTGAN.
2 code implementations • 19 Apr 2022 • Sarah Alnegheimish, Dongyu Liu, Carles Sala, Laure Berti-Equille, Kalyan Veeramachaneni
The detection of anomalies in time series data is a critical task with many monitoring applications.
no code implementations • 23 Feb 2022 • Alexandra Zytek, Ignacio Arnaldo, Dongyu Liu, Laure Berti-Equille, Kalyan Veeramachaneni
Through extensive experience developing and explaining machine learning (ML) applications for real-world domains, we have learned that ML models are only as interpretable as their features.
1 code implementation • 4 Aug 2021 • Furui Cheng, Dongyu Liu, Fan Du, Yanna Lin, Alexandra Zytek, Haomin Li, Huamin Qu, Kalyan Veeramachaneni
Machine learning (ML) is increasingly applied to Electronic Health Records (EHRs) to solve clinical prediction tasks.
1 code implementation • 17 Apr 2021 • Lei Xu, Alfredo Cuesta-Infante, Laure Berti-Equille, Kalyan Veeramachaneni
It improves the quality of adversarial examples by optimizing a critique score which combines the fluency, similarity, and misclassification metrics.
no code implementations • 2 Mar 2021 • Alexandra Zytek, Dongyu Liu, Rhema Vaithianathan, Kalyan Veeramachaneni
Machine learning (ML) is being applied to a diverse and ever-growing set of domains.
3 code implementations • 14 Dec 2020 • Micah J. Smith, Jürgen Cito, Kelvin Lu, Kalyan Veeramachaneni
While the open-source software development model has led to successful large-scale collaborations in building software systems, data science projects are frequently developed by individuals or small teams.
no code implementations • 22 Oct 2020 • Lei Xu, Ivan Ramirez, Kalyan Veeramachaneni
Most adversarial attack methods that are designed to deceive a text classifier change the text classifier's prediction by modifying a few words or characters.
no code implementations • 21 Oct 2020 • Shubhra Kanti Karmaker Santu, Md. Mahadi Hassan, Micah J. Smith, Lei Xu, ChengXiang Zhai, Kalyan Veeramachaneni
AutoML tools aim to make machine learning accessible for non-machine learning experts (domain experts), to improve the efficiency of machine learning, and to accelerate machine learning research.
3 code implementations • 1 Oct 2020 • Sarah Alnegheimish, Najat Alrashed, Faisal Aleissa, Shahad Althobaiti, Dongyu Liu, Mansour Alsaleh, Kalyan Veeramachaneni
An estimated 180 papers focusing on deep learning and EHR were published between 2010 and 2018.
5 code implementations • 16 Sep 2020 • Alexander Geiger, Dongyu Liu, Sarah Alnegheimish, Alfredo Cuesta-Infante, Kalyan Veeramachaneni
However, detecting anomalies in time series data is particularly challenging due to the vague definition of anomalies and said data's frequent lack of labels and highly complex temporal correlations.
no code implementations • CONLL 2019 • Shubhra Kanti Karmaker Santu, Kalyan Veeramachaneni, ChengXiang Zhai
Specifically, we propose a novel language model called Topical Influence Language Model (TILM), which is a novel extension of a neural language model to capture the influences on the contents in one text stream by the evolving topics in another related (or possibly same) text stream.
no code implementations • 25 Sep 2019 • Alexander Geiger, Alfredo Cuesta-Infante, Kalyan Veeramachaneni
Based on the recent developments in adversarially learned models, we propose a new approach for anomaly detection in time series data.
2 code implementations • 3 Sep 2019 • Kevin Alex Zhang, Lei Xu, Alfredo Cuesta-Infante, Kalyan Veeramachaneni
The goal of video watermarking is to embed a message within a video file in a way such that it minimally impacts the viewing experience but can be recovered even if the video is redistributed and modified, allowing media producers to assert ownership over their content.
no code implementations • 19 Aug 2019 • Yi Sun, Ivan Ramirez, Alfredo Cuesta-Infante, Kalyan Veeramachaneni
In many real life situations, including job and loan applications, gatekeepers must make justified and fair real-time decisions about a person's fitness for a particular opportunity.
9 code implementations • NeurIPS 2019 • Lei Xu, Maria Skoularidou, Alfredo Cuesta-Infante, Kalyan Veeramachaneni
Tabular data usually contains a mix of discrete and continuous columns.
no code implementations • 28 Jun 2019 • Lei Xu, Shubhra Kanti Karmaker Santu, Kalyan Veeramachaneni
In this paper, we tackle the challenge of defining useful prediction problems on event-driven time-series data.
8 code implementations • 22 May 2019 • Micah J. Smith, Carles Sala, James Max Kanter, Kalyan Veeramachaneni
To address these problems, we introduce the Machine Learning Bazaar, a new framework for developing machine learning and automated machine learning software systems.
1 code implementation • 13 Feb 2019 • Qianwen Wang, Yao Ming, Zhihua Jin, Qiaomu Shen, Dongyu Liu, Micah J. Smith, Kalyan Veeramachaneni, Huamin Qu
To guide the design of ATMSeer, we derive a workflow of using AutoML based on interviews with machine learning experts.
5 code implementations • 12 Jan 2019 • Kevin Alex Zhang, Alfredo Cuesta-Infante, Lei Xu, Kalyan Veeramachaneni
Image steganography is a procedure for hiding messages inside pictures.
no code implementations • 4 Dec 2018 • Yi Sun, Alfredo Cuesta-Infante, Kalyan Veeramachaneni
Moreover, we demonstrate that the model is able to generate high-quality samples in a variety of applications, making it a good candidate for synthetic data generation.
no code implementations • 29 Nov 2018 • Gaurav Sheni, Benjamin Schreck, Roy Wedge, James Max Kanter, Kalyan Veeramachaneni
In a head-to-head trial, reports generated utilizing full data science automation interface reports were funded 57. 5% of the time, while the ones that used baseline automation were only funded 42. 5% of the time.
7 code implementations • 27 Nov 2018 • Lei Xu, Kalyan Veeramachaneni
Generative adversarial networks (GANs) implicitly learn the probability distribution of a dataset and can draw samples from the distribution.
1 code implementation • 1 Jul 2018 • James Max Kanter, Benjamin Schreck, Kalyan Veeramachaneni
ML 2. 0: In this paper, we propose a paradigm shift from the current practice of creating machine learning models - which requires months-long discovery, exploration and "feasibility report" generation, followed by re-engineering for deployment - in favor of a rapid, 8-week process of development, understanding, validation and deployment that can executed by developers or subject matter experts (non-ML experts) using reusable APIs.
2 code implementations • 2017 IEEE International Conference on Big Data (Big Data) 2017 • Thomas Swearingen, Will Drevo, Bennett Cyphers, Alfredo Cuesta-Infante, Arun Ross, Kalyan Veeramachaneni
In this paper, we present Auto-Tuned Models, or ATM, a distributed, collaborative, scalable system for automated machine learning.
1 code implementation • 20 Oct 2017 • Roy Wedge, James Max Kanter, Santiago Moral Rubio, Sergio Iglesias Perez, Kalyan Veeramachaneni
In this paper, we present an automated feature engineering based approach to dramatically reduce false positives in fraud prediction.
1 code implementation • DSAA 2015 2015 • James Max Kanter, Kalyan Veeramachaneni
In this paper, we develop the Data Science Machine, which is able to derive predictive models from raw data automatically.
no code implementations • 14 Aug 2014 • Colin Taylor, Kalyan Veeramachaneni, Una-May O'Reilly
Even with more difficult prediction problems, such as predicting stop out at the end of the course with only one weeks' data, the models attained AUCs of 0. 7.