IEEE International Workshop on Fair and Interpretable Learning Algorithms
FILA 2020
- URL: https://fila-workshop.github.io/
- Event Date: 2020-12-10 ~ 2020-12-13
- Abstract Submission Date: 2020-09-25
- Submission Date: 2020-10-01
- Location: Atlanta, United States of America
IEEE International Workshop on Fair and Interpretable Learning Algorithms (FILA 2020)
December 10 - 13, 2020
Atlanta, GA, USA
https://fila-workshop.github.io/
In conjunction with the IEEE International Conference on Big Data (IEEE BigData 2020)
December 10 - 13, 2020
Atlanta Marriott Marquis
Atlanta, GA, USA
http://bigdataieee.org/BigData2020/
Introduction
With the proliferation of artificial intelligence (AI) and machine learning (ML) in every aspect of our automated, digital, and interconnected society, the issues of fairness, explainability and interpretability of AI and ML algorithms have become very important. If the output of an algorithm in response to a query is not transparent to or interpretable by humans, then they will always have questions about it’s correctness and fairness. An algorithm is considered to be fair, if its results are independent of some sensitive but unrelated variables (e.g., gender, race, ethnicity, sexual orientation). For an algorithm to be interpretable, it should not only output the results, but also produce a certificate showing that the results that it has computed are according to the expected specifications. This is our motivation to organize the International Workshop on Fair and Interpretable Learning Algorithms (FILA 2020).
The objectives of the FILA 2020 workshop are to:
o Provide a venue for academic researchers, industry professionals, and government partners to come together, present and discuss research results, use cases, innovative ideas, challenges, and opportunities that arise from designing machine learning applications and big data analytics solutions using novel, efficient, scalable, fair and interpretable AI and ML algorithms.
o Foster collaboration between Algorithms | Theoretical Computer Science communities and Artificial Intelligence | Machine Learning | Data Science | Network Science communities.
The predecessor of FILA, ParLearning has been organized annually at IPDPS from 2012 - 2018 and at KDD in 2019. In 2019, ParLearning was organized as a half-day workshop. It accepted 3 regular papers for publication and presentation from 20 submissions. There were 3 invited talks by Professor V.S. Subrahmanian (Dartmouth College, Hanover, NH, USA), Dr. Lifeng Nai (Google Research, Mountain View, CA, USA), and Dr. Satish Nadathur (Facebook Research, Menlo Park, CA, USA). The workshop was well-attended by more than 100 people, with almost all seats occupied.
For 2020, the technical focus will change from parallel and distributed learning to fair and interpretable algorithmic learning. The Organizing Committee and Technical Program Committee have been expanded to include selected authors of accepted papers from ParLearning 2019.
Call for Papers
The FILA 2020 conference is focused on fairness and interpretability of machine learning algorithms. We invite submissions with contributions to new or existing learning probles including, but not limited to:
o Design and analysis of fair and interpretable machine learning algorithms
o Statistical and computational complexity of fair and interpretable machine learning
o Optimization methods for fair and interpretable learning
o Fairness in online and stochastic optimization
o Fair machine learning through Bayesian methods
o Fairness game theory and machine learning
o Interpretable machine learning from complex data (e.g., networks, time series)
o Fairness and interpretability in learning for particular settings (e.g., computational social science, economics, climate)
o Algorithmic unfairness and bias in popularly used learning datasets
o Fairness, accountability, transparency, and ethics in search
o Fairness-aware recommender systems and diversity in recommendation
o Investigation of black-box systems, particularly web platforms and algorithms
o Transparency-aware algorithms for social impact
o Fairness audits on the use of sensitive data
o Evaluation methods for fair and interpretable machine learning
o Fairness in unsupervised machine learning (e.g., clustering)
o Fairness in reinforcement learning
o Interpretability of neural network algorithms
o Accountability in human-in-the-loop machine learning
o Privacy-preserving and fairness-aware machine learning
Important Dates (All times are Anywhere on Earth)
o Paper Submission: October 1, 2020
o Notification: November 1, 2020
o Camera Ready: November 15, 2020
o Workshop: December 10 - 13, 2020
Paper Guidelines
Coming soon.
Keynote Speakers
o Professor Krishna P. Gummadi (Max Planck Institute for Software Systems, Saarbrücken, Germany)
o Professor Hanghang Tong (University of Illinois at Urbana-Champaign, Urbana, IL, USA)
o Professor Auroop Ratan Ganguly (Northeastern University, Boston, MA, USA)
Organization
General Chairs:
o Arindam Pal (Data61, CSIRO and Cyber Security CRC, Sydney, New South Wales, Australia)
o Yinglong Xia (Facebook AI, Santa Clara, CA, USA)
Program Chairs:
o Abhijnan Chakraborty (Max Planck Institute for Software Systems, Saarbrücken, Germany)
o Mayank Singh (IIT Gandhinagar, Gujarat, India)
December 10 - 13, 2020
Atlanta, GA, USA
https://fila-workshop.github.io/
In conjunction with the IEEE International Conference on Big Data (IEEE BigData 2020)
December 10 - 13, 2020
Atlanta Marriott Marquis
Atlanta, GA, USA
http://bigdataieee.org/BigData2020/
Introduction
With the proliferation of artificial intelligence (AI) and machine learning (ML) in every aspect of our automated, digital, and interconnected society, the issues of fairness, explainability and interpretability of AI and ML algorithms have become very important. If the output of an algorithm in response to a query is not transparent to or interpretable by humans, then they will always have questions about it’s correctness and fairness. An algorithm is considered to be fair, if its results are independent of some sensitive but unrelated variables (e.g., gender, race, ethnicity, sexual orientation). For an algorithm to be interpretable, it should not only output the results, but also produce a certificate showing that the results that it has computed are according to the expected specifications. This is our motivation to organize the International Workshop on Fair and Interpretable Learning Algorithms (FILA 2020).
The objectives of the FILA 2020 workshop are to:
o Provide a venue for academic researchers, industry professionals, and government partners to come together, present and discuss research results, use cases, innovative ideas, challenges, and opportunities that arise from designing machine learning applications and big data analytics solutions using novel, efficient, scalable, fair and interpretable AI and ML algorithms.
o Foster collaboration between Algorithms | Theoretical Computer Science communities and Artificial Intelligence | Machine Learning | Data Science | Network Science communities.
The predecessor of FILA, ParLearning has been organized annually at IPDPS from 2012 - 2018 and at KDD in 2019. In 2019, ParLearning was organized as a half-day workshop. It accepted 3 regular papers for publication and presentation from 20 submissions. There were 3 invited talks by Professor V.S. Subrahmanian (Dartmouth College, Hanover, NH, USA), Dr. Lifeng Nai (Google Research, Mountain View, CA, USA), and Dr. Satish Nadathur (Facebook Research, Menlo Park, CA, USA). The workshop was well-attended by more than 100 people, with almost all seats occupied.
For 2020, the technical focus will change from parallel and distributed learning to fair and interpretable algorithmic learning. The Organizing Committee and Technical Program Committee have been expanded to include selected authors of accepted papers from ParLearning 2019.
Call for Papers
The FILA 2020 conference is focused on fairness and interpretability of machine learning algorithms. We invite submissions with contributions to new or existing learning probles including, but not limited to:
o Design and analysis of fair and interpretable machine learning algorithms
o Statistical and computational complexity of fair and interpretable machine learning
o Optimization methods for fair and interpretable learning
o Fairness in online and stochastic optimization
o Fair machine learning through Bayesian methods
o Fairness game theory and machine learning
o Interpretable machine learning from complex data (e.g., networks, time series)
o Fairness and interpretability in learning for particular settings (e.g., computational social science, economics, climate)
o Algorithmic unfairness and bias in popularly used learning datasets
o Fairness, accountability, transparency, and ethics in search
o Fairness-aware recommender systems and diversity in recommendation
o Investigation of black-box systems, particularly web platforms and algorithms
o Transparency-aware algorithms for social impact
o Fairness audits on the use of sensitive data
o Evaluation methods for fair and interpretable machine learning
o Fairness in unsupervised machine learning (e.g., clustering)
o Fairness in reinforcement learning
o Interpretability of neural network algorithms
o Accountability in human-in-the-loop machine learning
o Privacy-preserving and fairness-aware machine learning
Important Dates (All times are Anywhere on Earth)
o Paper Submission: October 1, 2020
o Notification: November 1, 2020
o Camera Ready: November 15, 2020
o Workshop: December 10 - 13, 2020
Paper Guidelines
Coming soon.
Keynote Speakers
o Professor Krishna P. Gummadi (Max Planck Institute for Software Systems, Saarbrücken, Germany)
o Professor Hanghang Tong (University of Illinois at Urbana-Champaign, Urbana, IL, USA)
o Professor Auroop Ratan Ganguly (Northeastern University, Boston, MA, USA)
Organization
General Chairs:
o Arindam Pal (Data61, CSIRO and Cyber Security CRC, Sydney, New South Wales, Australia)
o Yinglong Xia (Facebook AI, Santa Clara, CA, USA)
Program Chairs:
o Abhijnan Chakraborty (Max Planck Institute for Software Systems, Saarbrücken, Germany)
o Mayank Singh (IIT Gandhinagar, Gujarat, India)
Journal Promotion
|
| Acta Koreana (Acta Koreana) |
|
| Acta Via Serica (AVS) |
|
| Computers and Concrete (CAC) |
|
| Journal of Information Processing Systems (JIPS) |
|
| Journal of Internet Computing and Services (KSII - JICS) |
|
| Journal of Smart Tourism (Smart Tourism) |
|
| Membrane and Water Treatment (MWT) |
|
| Wind and Structures, An International Journal (Wind and Structures) |
MANUSCRIPTLINK © 2015 -
