no code implementations • 19 Apr 2024 • Qinyuan Wu, Mohammad Aflah Khan, Soumi Das, Vedant Nanda, Bishwamittra Ghosh, Camila Kolling, Till Speicher, Laurent Bindschaedler, Krishna P. Gummadi, Evimaria Terzi
We propose an approach for estimating the latent knowledge embedded inside large language models (LLMs).
no code implementations • 27 Mar 2024 • Abhisek Dash, Abhijnan Chakraborty, Saptarshi Ghosh, Animesh Mukherjee, Jens Frankenreiter, Stefan Bechtold, Krishna P. Gummadi
In digital markets, antitrust law and special regulations aim to ensure that markets remain competitive despite the dominating role that digital platforms play today in everyone's life.
no code implementations • 30 May 2023 • Camila Kolling, Till Speicher, Vedant Nanda, Mariya Toneva, Krishna P. Gummadi
Concretely, we show how PNKA can be leveraged to develop a deeper understanding of (a) the input examples that are likely to be misclassified, (b) the concepts encoded by (individual) neurons in a layer, and (c) the effects of fairness interventions on learned representations.
1 code implementation • 23 Jun 2022 • Vedant Nanda, Till Speicher, Camila Kolling, John P. Dickerson, Krishna P. Gummadi, Adrian Weller
Our work offers a new view on robustness by using another reference NN to define the set of perturbations a given NN should be invariant to, thus generalizing the reliance on a reference ``human NN'' to any NN.
1 code implementation • 10 May 2022 • Miriam Rateike, Ayan Majumdar, Olga Mineeva, Krishna P. Gummadi, Isabel Valera
In addition, data is often selectively labeled, i. e., even the biased labels are only observed for a small fraction of the data that received a positive decision.
1 code implementation • 26 Apr 2022 • Gourab K. Patro, Prithwish Jana, Abhijnan Chakraborty, Krishna P. Gummadi, Niloy Ganguly
As the efficiency and fairness objectives can be in conflict with each other, we propose a joint optimization framework that allows conference organizers to design schedules that balance (i. e., allow trade-offs) among efficiency, participant fairness and speaker fairness objectives.
1 code implementation • 1 Apr 2022 • Abhisek Dash, Abhijnan Chakraborty, Saptarshi Ghosh, Animesh Mukherjee, Krishna P. Gummadi
To this end, our experiments on multiple real-world RIR datasets reveal that the existing RIR algorithms often result in very skewed exposure distribution of items, and the quality of items is not a plausible explanation for such skew in exposure.
no code implementations • 8 Feb 2022 • Abhisek Dash, Abhijnan Chakraborty, Saptarshi Ghosh, Animesh Mukherjee, Krishna P. Gummadi
While investigating for the fairness of the default action, we observe that over a set of as many as 1000 queries, in nearly 68% cases, there exist one or more products which are more relevant (as per Amazon's own desktop search results) than the product chosen by Alexa.
1 code implementation • 26 Dec 2021 • Arpita Biswas, Gourab K Patro, Niloy Ganguly, Krishna P. Gummadi, Abhijnan Chakraborty
Many online platforms today (such as Amazon, Netflix, Spotify, LinkedIn, and AirBnB) can be thought of as two-sided markets with producers and customers of goods and services.
no code implementations • 10 Dec 2021 • Vitalii Emelianov, Nicolas Gast, Krishna P. Gummadi, Patrick Loiseau
In the second setting (with known variances), imposing the $\gamma$-rule decreases the utility but we prove a bound on the utility loss due to the fairness mechanism.
1 code implementation • 29 Nov 2021 • Vedant Nanda, Ayan Majumdar, Camila Kolling, John P. Dickerson, Krishna P. Gummadi, Bradley C. Love, Adrian Weller
One necessary criterion for a network's invariances to align with human perception is for its IRIs look 'similar' to humans.
no code implementations • 9 Sep 2021 • Preethi Lahoti, Krishna P. Gummadi, Gerhard Weikum
Reliably predicting potential failure risks of machine learning (ML) systems when deployed with production data is a crucial aspect of trustworthy AI.
no code implementations • 10 May 2021 • Junaid Ali, Muhammad Bilal Zafar, Adish Singla, Krishna P. Gummadi
Motivated by extensive literature in behavioral economics and behavioral psychology (prospect theory), we propose a notion of fair updates that we refer to as loss-averse updates.
no code implementations • 10 May 2021 • Junaid Ali, Preethi Lahoti, Krishna P. Gummadi
We further propose methods to achieve our goal of equalizing group error rates arising due to model uncertainty in algorithmic decision making and demonstrate the effectiveness of these methods using synthetic and real-world datasets.
1 code implementation • 6 May 2021 • Ahmad Khajehnejad, Moein Khajehnejad, Mahmoudreza Babaei, Krishna P. Gummadi, Adrian Weller, Baharan Mirzasoleiman
The potential for machine learning systems to amplify social inequities and unfairness is receiving increasing popular and academic attention.
no code implementations • 30 Jan 2021 • Abhisek Dash, Abhijnan Chakraborty, Saptarshi Ghosh, Animesh Mukherjee, Krishna P. Gummadi
Along a number of our proposed bias measures, we find that the sponsored recommendations are significantly more biased toward Amazon private label products compared to organic recommendations.
no code implementations • 24 Oct 2020 • Gourab K Patro, Abhijnan Chakraborty, Niloy Ganguly, Krishna P. Gummadi
We show that the welfare and fairness objectives can be in conflict with each other, and there is a need to maintain a balance between these objective while caring for them simultaneously.
no code implementations • 1 Jul 2020 • Vedant Nanda, Till Speicher, John P. Dickerson, Krishna P. Gummadi, Muhammad Bilal Zafar
Our framework defines a large number of concepts that the DNN explanations could be based on and performs the explanation-conformity check at test time to assess prediction robustness.
no code implementations • 24 Jun 2020 • Vitalii Emelianov, Nicolas Gast, Krishna P. Gummadi, Patrick Loiseau
We then compare the utility obtained by imposing a fairness mechanism that we term $\gamma$-rule (it includes demographic parity and the four-fifths rule as special cases), to that of a group-oblivious selection algorithm that picks the candidates with the highest estimated quality independently of their group.
no code implementations • 19 May 2020 • Bashir Rastegarpanah, Mark Crovella, Krishna P. Gummadi
We show that for an optimal classifier these three properties are in general incompatible, and we explain what common properties of data make them incompatible.
2 code implementations • 25 Feb 2020 • Gourab K Patro, Arpita Biswas, Niloy Ganguly, Krishna P. Gummadi, Abhijnan Chakraborty
We investigate the problem of fair recommendation in the context of two-sided online platforms, comprising customers on one side and producers on the other.
no code implementations • 30 Oct 2019 • Michiel A. Bakker, Duy Patrick Tu, Humberto Riverón Valdés, Krishna P. Gummadi, Kush R. Varshney, Adrian Weller, Alex Pentland
We introduce a framework for dynamic adversarial discovery of information (DADI), motivated by a scenario where information (a feature set) is used by third parties with unknown objectives.
1 code implementation • 22 Oct 2019 • Hanchen Wang, Nina Grgic-Hlaca, Preethi Lahoti, Krishna P. Gummadi, Adrian Weller
We do not provide a way to directly learn a similarity metric satisfying the individual fairness, but to provide an empirical study on how to derive the similarity metric from human supervisors, then future work can use this as a tool to understand human supervision.
no code implementations • 2 Jul 2019 • Preethi Lahoti, Krishna P. Gummadi, Gerhard Weikum
We revisit the notion of individual fairness proposed by Dwork et al. A central challenge in operationalizing their approach is the difficulty in eliciting a human specification of a similarity metric.
no code implementations • 16 May 2019 • Junaid Ali, Mahmoudreza Babaei, Abhijnan Chakraborty, Baharan Mirzasoleiman, Krishna P. Gummadi, Adish Singla
As we show in this paper, the time-criticality of the information could further exacerbate the disparity of influence across groups.
Social and Information Networks Computers and Society
1 code implementation • 4 Mar 2019 • Hoda Heidari, Vedant Nanda, Krishna P. Gummadi
Most existing notions of algorithmic fairness are one-shot: they ensure some form of allocative equality at the time of decision making, but do not account for the adverse impact of the algorithmic decisions today on the long-term welfare and prosperity of certain segments of the population.
1 code implementation • 2 Dec 2018 • Bashir Rastegarpanah, Krishna P. Gummadi, Mark Crovella
We take as our model system the matrix factorization approach to recommendation, and we propose a set of measures to capture the polarization or fairness of recommendations.
no code implementations • 10 Sep 2018 • Hoda Heidari, Michele Loi, Krishna P. Gummadi, Andreas Krause
In this respect, our work serves as a unifying moral framework for understanding existing notions of algorithmic fairness.
no code implementations • 2 Jul 2018 • Till Speicher, Hoda Heidari, Nina Grgic-Hlaca, Krishna P. Gummadi, Adish Singla, Adrian Weller, Muhammad Bilal Zafar
Further, our work reveals overlooked tradeoffs between different fairness notions: using our proposed measures, the overall individual-level unfairness of an algorithm can be decomposed into a between-group and a within-group component.
no code implementations • NeurIPS 2018 • Hoda Heidari, Claudio Ferrari, Krishna P. Gummadi, Andreas Krause
We draw attention to an important, yet largely overlooked aspect of evaluating fairness for automated decision making systems---namely risk and welfare considerations.
1 code implementation • ICML 2018 • Niki Kilbertus, Adrià Gascón, Matt J. Kusner, Michael Veale, Krishna P. Gummadi, Adrian Weller
Recent work has explored how to train machine learning models which do not discriminate against any subgroup of the population as determined by sensitive attributes such as gender or race.
no code implementations • 4 Jun 2018 • Preethi Lahoti, Krishna P. Gummadi, Gerhard Weikum
We demonstrate the versatility of our method by applying it to classification and learning-to-rank tasks on a variety of real-world datasets.
no code implementations • 4 May 2018 • Asia J. Biega, Krishna P. Gummadi, Gerhard Weikum
We formulate the challenge of achieving amortized individual fairness subject to constraints on ranking quality as an online optimization problem and show that it can be solved as an integer linear program.
no code implementations • 26 Feb 2018 • Nina Grgić-Hlača, Elissa M. Redmiles, Krishna P. Gummadi, Adrian Weller
As algorithms are increasingly used to make important decisions that affect human lives, ranging from social benefit assignment to predicting risk of criminal recidivism, concerns have been raised about the fairness of algorithmic decision making.
1 code implementation • NeurIPS 2017 • Muhammad Bilal Zafar, Isabel Valera, Manuel Gomez Rodriguez, Krishna P. Gummadi, Adrian Weller
The adoption of automated, data-driven decision making in an ever expanding range of applications has raised concerns about its potential unfairness towards certain social groups.
no code implementations • 30 Jun 2017 • Nina Grgić-Hlača, Muhammad Bilal Zafar, Krishna P. Gummadi, Adrian Weller
Consider a binary decision making process where a single machine learning classifier replaces a multitude of humans.
no code implementations • 31 Oct 2016 • Miguel Ferreira, Muhammad Bilal Zafar, Krishna P. Gummadi
Bringing transparency to black-box decision making systems (DMS) has been a topic of increasing research interest in recent years.
3 code implementations • 26 Oct 2016 • Muhammad Bilal Zafar, Isabel Valera, Manuel Gomez Rodriguez, Krishna P. Gummadi
To account for and avoid such unfairness, in this paper, we introduce a new notion of unfairness, disparate mistreatment, which is defined in terms of misclassification rates.
2 code implementations • 19 Jul 2015 • Muhammad Bilal Zafar, Isabel Valera, Manuel Gomez Rodriguez, Krishna P. Gummadi
Algorithmic decision making systems are ubiquitous across a wide variety of online as well as offline services.