Semi-supervised counterfactual explanations

no code implementations • 22 Mar 2023 • Shravan Kumar Sajja, Sumanta Mukherjee, Satyam Dwivedi

Counterfactual explanations for machine learning models are used to find minimal interventions to the feature values such that the model changes the prediction to a different output or a target output.

counterfactual Counterfactual Explanation +1

Alexa Teacher Model: Pretraining and Distilling Multi-Billion-Parameter Encoders for Natural Language Understanding Systems

no code implementations • 15 Jun 2022 • Jack FitzGerald, Shankar Ananthakrishnan, Konstantine Arkoudas, Davide Bernardi, Abhishek Bhagia, Claudio Delli Bovi, Jin Cao, Rakesh Chada, Amit Chauhan, Luoxin Chen, Anurag Dwarakanath, Satyam Dwivedi, Turan Gojayev, Karthik Gopalakrishnan, Thomas Gueudre, Dilek Hakkani-Tur, Wael Hamza, Jonathan Hueser, Kevin Martin Jose, Haidar Khan, Beiye Liu, Jianhua Lu, Alessandro Manzotti, Pradeep Natarajan, Karolina Owczarzak, Gokmen Oz, Enrico Palumbo, Charith Peris, Chandana Satya Prakash, Stephen Rawls, Andy Rosenbaum, Anjali Shenoy, Saleh Soltan, Mukund Harakere Sridhar, Liz Tan, Fabian Triefenbach, Pan Wei, Haiyang Yu, Shuai Zheng, Gokhan Tur, Prem Natarajan

We present results from a large-scale experiment on pretraining encoders with non-embedding parameter counts ranging from 700M to 9. 3B, their subsequent distillation into smaller models ranging from 17M-170M parameters, and their application to the Natural Language Understanding (NLU) component of a virtual assistant system.

Cross-Lingual Natural Language Inference intent-classification +5

Semi-Passive 3D Positioning of Multiple RIS-Enabled Users

no code implementations • 25 Apr 2021 • Kamran Keykhosravi, Musa Furkan Keskin, Satyam Dwivedi, Gonzalo Seco-Granados, Henk Wymeersch

In this work, we study the application of RIS in a multi-user passive localization scenario, where we have one transmitter (Tx) and multiple asynchronous receivers (Rxs) with known locations.

5G New Radio for Public Safety Mission Critical Communications

no code implementations • 3 Mar 2021 • Jingya Li, Keerthi Kumar Nagalapur, Erik Stare, Satyam Dwivedi, Shehzad Ali Ashraf, Per-Erik Eriksson, Ulrika Engström, Woonghee Lee, Thorsten Lohmar

Driven by increasing demands on connectivity to improve safety, situational awareness and operational effectiveness for first responders, more and more public safety agencies are realizing the need of modernization of their existing non-3GPP networks.

Networking and Internet Architecture

Positioning in 5G networks

no code implementations • 5 Feb 2021 • Satyam Dwivedi, Ritesh Shreevastav, Florent Munier, Johannes Nygren, Iana Siomina, Yazid Lyazidi, Deep Shrestha, Gustav Lindmark, Per Ernström, Erik Stare, Sara M. Razavi, Siva Muruganathan, Gino Masini, Åke Busin, Fredrik Gunnarsson

In this paper we describe the recent 3GPP Release 16 specification for positioning in 5G networks.

Networking and Internet Architecture

Robust Localization in Wireless Networks From Corrupted Signals

1 code implementation • 9 Oct 2020 • Muhammad Osama, Dave Zachariah, Satyam Dwivedi, Petre Stoica

We address the problem of timing-based localization in wireless networks, when an unknown fraction of data is corrupted by nonideal signal conditions.

Attention based Multi-Modal New Product Sales Time-series Forecasting

1 code implementation • ACM SIGKDD International Conference on Knowledge Discovery & Data Mining 2020 • Vijay Ekambaram, Kushagra Manglik, Sumanta Mukherjee, SURYA SHRAVAN KUMAR SAJJA, Satyam Dwivedi, Vikas Raykar

Trend driven retail industries such as fashion, launch substantial new products every season.

New Product Sales Forecasting Short-observation new product sales forecasting +1