no code implementations • 22 Apr 2024 • Jesse Thibodeau, Hadi Nekoei, Afaf Taïk, Janarthanan Rajendran, Golnoosh Farnadi
We find that, upon deploying a learned tax and redistribution policy, social welfare improves on that of the fairness-agnostic baseline, and approaches that of the analytically optimal fairness-aware baseline for the multi-armed and contextual bandit settings, and surpassing it by 13. 19% in the full RL setting.
no code implementations • 20 Mar 2024 • Khaoula Chehbouni, Megha Roshan, Emmanuel Ma, Futian Andrew Wei, Afaf Taik, Jackie CK Cheung, Golnoosh Farnadi
Despite growing mitigation efforts to develop safety safeguards, such as supervised safety-oriented fine-tuning and leveraging safe reinforcement learning from human feedback, multiple concerns regarding the safety and ingrained biases in these models remain.
2 code implementations • 31 Oct 2023 • Meraj Hashemizadeh, Juan Ramirez, Rohan Sukumaran, Golnoosh Farnadi, Simon Lacoste-Julien, Jose Gallego-Posada
Model pruning is a popular approach to enable the deployment of large deep learning models on edge devices with restricted computational or storage capacities.
no code implementations • 30 Oct 2023 • Ahmad-Reza Ehyaei, Golnoosh Farnadi, Samira Samadi
Despite the essential need for comprehensive considerations in responsible AI, factors like robustness, fairness, and causality are often studied in isolation.
no code implementations • 5 Sep 2023 • Armin Moradi, Golnoosh Farnadi
The growing popularity of language models has sparked interest in conversational recommender systems (CRS) within both industry and research circles.
no code implementations • 28 Aug 2023 • Rebecca Salganik, Fernando Diaz, Golnoosh Farnadi
As online music platforms grow, music recommender systems play a vital role in helping users navigate and discover content within their vast musical databases.
no code implementations • 17 Aug 2023 • Ahmad-Reza Ehyaei, Kiarash Mohammadi, Amir-Hossein Karimi, Samira Samadi, Golnoosh Farnadi
In this paper, we propose a novel approach that examines the relationship between individual fairness, adversarial robustness, and structural causal models in heterogeneous data spaces, particularly when dealing with discrete sensitive attributes.
no code implementations • 11 Jun 2023 • Maryam Molamohammadi, Afaf Taik, Nicolas Le Roux, Golnoosh Farnadi
The growing utilization of machine learning (ML) in decision-making processes raises questions about its benefits to society.
no code implementations • 6 Mar 2023 • Jia Ao Sun, Sikha Pentyala, Martine De Cock, Golnoosh Farnadi
Users worldwide access massive amounts of curated data in the form of rankings on a daily basis.
1 code implementation • 8 Sep 2022 • Rebecca Salganik, Fernando Diaz, Golnoosh Farnadi
We evaluate two popular GNN methods: Graph Convolutional Network (GCN), which trains on the entire graph, and GraphSAGE, which uses probabilistic random walks to create subgraphs for mini-batch training, and assess the effects of sub-sampling on individual fairness.
no code implementations • 1 Jun 2022 • Kiarash Mohammadi, Aishwarya Sivaraman, Golnoosh Farnadi
Empirical evaluation on real-world datasets indicates that FETA is not only able to guarantee fairness on-the-fly at prediction time but also is able to train accurate models exhibiting a much higher degree of individual fairness.
no code implementations • 23 May 2022 • Sikha Pentyala, Nicola Neophytou, Anderson Nascimento, Martine De Cock, Golnoosh Farnadi
Group fairness ensures that the outcome of machine learning (ML) based decision making systems are not biased towards a certain group of people defined by a sensitive attribute such as gender or ethnicity.
1 code implementation • 8 Feb 2022 • Sikha Pentyala, David Melanson, Martine De Cock, Golnoosh Farnadi
Machine learning (ML) has become prominent in applications that directly affect people's quality of life, including in healthcare, justice, and finance.
no code implementations • AAAI Workshop CLeaR 2022 • Kiarash Mohammadi, Aishwarya Sivaraman, Golnoosh Farnadi
There is an increasing interest in adopting high-capacity machine learning models such as deep neural networks to semi-automate human decisions.
1 code implementation • NeurIPS 2020 • Aishwarya Sivaraman, Golnoosh Farnadi, Todd Millstein, Guy Van Den Broeck
Additionally, we propose a technique to use monotonicity as an inductive bias for deep learning.
no code implementations • 5 Jan 2020 • Golnoosh Farnadi, Lise Getoor, Marie-Francine Moens, Martine De Cock
In this paper, we propose a mechanism to infer a variety of user characteristics, such as, age, gender and personality traits, which can then be compiled into a user profile.
no code implementations • 23 Sep 2019 • Behrouz Babaki, Golnoosh Farnadi, Gilles Pesant
In this paper we show how identifying and exploiting these identical subproblems can simplify solving them and leads to a compact representation of the solution.
1 code implementation • 10 Jun 2019 • YooJung Choi, Golnoosh Farnadi, Behrouz Babaki, Guy Van Den Broeck
As machine learning is increasingly used to make real-world decisions, recent research efforts aim to define and ensure fairness in algorithmic decision making.
no code implementations • 30 Aug 2018 • Sisi Wang, Wing-Sea Poon, Golnoosh Farnadi, Caleb Horst, Kebra Thompson, Michael Nickels, Rafael Dowsley, Anderson C. A. Nascimento, Martine De Cock
User profiling from user generated content (UGC) is a common practice that supports the business models of many social media companies.
no code implementations • 3 Jul 2018 • Varun Embar, Dhanya Sridhar, Golnoosh Farnadi, Lise Getoor
We introduce a greedy search-based algorithm and a novel optimization method that trade-off scalability and approximations to the structure learning problem in varying ways.