Timezone: »
Machine Learning models are often susceptible to poor performance on instances sampled from bad environments. For example, an image classifier could provide low accuracy on images captured under low lighting conditions. In high stake ML applications, such as AI-driven medical diagnostics, a better option could be to provide recourse in the form of alternative environment settings in which to recapture the instance for more reliable diagnostics. In this paper, we propose a model called {\em RecourseNet} that learns to apply recourse on the space of environments so that the recoursed instances are amenable to better predictions by the classifier. Learning to output optimal recourse is challenging because we do not assume access to the underlying physical process that generates the recoursed instances. Also, the optimal setting could be instance-dependent --- for example the best camera angle for object recognition could be a function of the object's shape. We propose a novel three-level training method that (a) Learns a classifier that is optimized for high performance under recourse, (b) Learns a recourse predictor when the training data may contain only limited instances under good environment settings, and (c) Triggers recourse selectively only when recourse is likely to improve classifier confidence.
Author Information
Lokesh N (IIT Bombay)
I was a masters student in IISc Bangalore. I am currently working at IBM Research-India
Guntakanti Sai Koushik (Indian Institute of Technology, Bombay)
Abir De (IIT Bombay)
Sunita Sarawagi (IIT Bombay)
More from the Same Authors
-
2022 : Learning Cross-Database Transfer of Text-queries for Adapting Text-to-SQL Parsers »
Abhijeet Awasthi · Ashutosh Sathe · Sunita Sarawagi -
2023 Poster: Locality Sensitive Hashing in Fourier Frequency Domain For Soft Set Containment Search »
Indradyumna Roy · Rishi Agarwal · Soumen Chakrabarti · Anirban Dasgupta · Abir De -
2023 Poster: Learning to Select a Subset of Training Examples to Generalize Efficient Model Training »
Eeshaan Jain · Tushar Nandy · Gaurav Aggarwal · Ashish Tendulkar · Rishabh Iyer · Abir De -
2022 Spotlight: Neural Estimation of Submodular Functions with Applications to Differentiable Subset Selection »
Abir De · Soumen Chakrabarti -
2022 Spotlight: Maximum Common Subgraph Guided Graph Retrieval: Late and Early Interaction Networks »
Indradyumna Roy · Soumen Chakrabarti · Abir De -
2022 Spotlight: Learning Recourse on Instance Environment to Enhance Prediction Accuracy »
Lokesh N · Guntakanti Sai Koushik · Abir De · Sunita Sarawagi -
2022 Poster: Neural Estimation of Submodular Functions with Applications to Differentiable Subset Selection »
Abir De · Soumen Chakrabarti -
2022 Poster: Maximum Common Subgraph Guided Graph Retrieval: Late and Early Interaction Networks »
Indradyumna Roy · Soumen Chakrabarti · Abir De -
2021 Poster: Learning to Select Exogenous Events for Marked Temporal Point Process »
Ping Zhang · Rishabh Iyer · Ashish Tendulkar · Gaurav Aggarwal · Abir De -
2021 Poster: Active Assessment of Prediction Services as Accuracy Surface Over Attribute Combinations »
Vihari Piratla · Soumen Chakrabarti · Sunita Sarawagi -
2021 : Live Q&A with Sunita Sarawagi »
Sunita Sarawagi -
2021 : Invited talk - Machine Learning as a Service: The Challenges of Serving diverse client Distributions, Sunita Sarawagi »
Sunita Sarawagi -
2021 Poster: Differentiable Learning Under Triage »
Nastaran Okati · Abir De · Manuel Rodriguez -
2021 Poster: Training for the Future: A Simple Gradient Interpolation Loss to Generalize Along Time »
Anshul Nasery · Soumyadeep Thakur · Vihari Piratla · Abir De · Sunita Sarawagi -
2021 Poster: Counterfactual Explanations in Sequential Decision Making Under Uncertainty »
Stratis Tsirtsis · Abir De · Manuel Rodriguez -
2019 : Poster Session »
Ayse Cakmak · Yunkai Zhang · Srijith Prabhakarannair Kusumam · Mohamed Osama Ahmed · Xintao Wu · Jayesh Choudhari · David I Inouye · Thomas Taylor · Michel Besserve · Ali Caner Turkmen · Kazi Islam · Antonio Artés · Amrith Setlur · Zhanghua Fu · Zhen Han · Abir De · Nan Du · Pablo Sanchez-Martin -
2018 Poster: Deep Reinforcement Learning of Marked Temporal Point Processes »
Utkarsh Upadhyay · Abir De · Manuel Gomez Rodriguez -
2016 Poster: Learning and Forecasting Opinion Dynamics in Social Networks »
Abir De · Isabel Valera · Niloy Ganguly · Sourangshu Bhattacharya · Manuel Gomez Rodriguez -
2010 Oral: MAP estimation in Binary MRFs via Bipartite Multi-cuts »
Sashank Jakkam Reddi · Sunita Sarawagi · Sundar Vishwanathan -
2010 Poster: MAP estimation in Binary MRFs via Bipartite Multi-cuts »
Sashank Jakkam Reddi · Sunita Sarawagi · Sundar Vishwanathan