Search Results for author: Krishna P. Gummadi

Found 39 papers, 15 papers with code

Antitrust, Amazon, and Algorithmic Auditing

no code implementations27 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.

Pointwise Representational Similarity

no code implementations30 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.


Measuring Representational Robustness of Neural Networks Through Shared Invariances

1 code implementation23 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.

Don't Throw it Away! The Utility of Unlabeled Data in Fair Decision Making

1 code implementation10 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.

Decision Making Fairness

Scheduling Virtual Conferences Fairly: Achieving Equitable Participant and Speaker Satisfaction

1 code implementation26 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.

Fairness Scheduling

FaiRIR: Mitigating Exposure Bias from Related Item Recommendations in Two-Sided Platforms

1 code implementation1 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.

Alexa, in you, I trust! Fairness and Interpretability Issues in E-commerce Search through Smart Speakers

no code implementations8 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.


Towards Fair Recommendation in Two-Sided Platforms

1 code implementation26 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.

Fairness Vocal Bursts Valence Prediction

On Fair Selection in the Presence of Implicit and Differential Variance

no code implementations10 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.


Detecting and Mitigating Test-time Failure Risks via Model-agnostic Uncertainty Learning

no code implementations9 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.

Accounting for Model Uncertainty in Algorithmic Discrimination

no code implementations10 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.

Decision Making Fairness

Loss-Aversively Fair Classification

no code implementations10 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.

Classification Decision Making +2

CrossWalk: Fairness-enhanced Node Representation Learning

1 code implementation6 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.

Fairness Link Prediction +2

When the Umpire is also a Player: Bias in Private Label Product Recommendations on E-commerce Marketplaces

no code implementations30 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.


On Fair Virtual Conference Scheduling: Achieving Equitable Participant and Speaker Satisfaction

no code implementations24 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.

Fairness Scheduling

Unifying Model Explainability and Robustness via Machine-Checkable Concepts

no code implementations1 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.

On Fair Selection in the Presence of Implicit Variance

no code implementations24 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.


Fair Inputs and Fair Outputs: The Incompatibility of Fairness in Privacy and Accuracy

no code implementations19 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.

Decision Making Fairness

FairRec: Two-Sided Fairness for Personalized Recommendations in Two-Sided Platforms

2 code implementations25 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.

Fairness Vocal Bursts Valence Prediction

DADI: Dynamic Discovery of Fair Information with Adversarial Reinforcement Learning

no code implementations30 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.

Fairness reinforcement-learning +2

An Empirical Study on Learning Fairness Metrics for COMPAS Data with Human Supervision

1 code implementation22 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.

Fairness Metric Learning

Operationalizing Individual Fairness with Pairwise Fair Representations

no code implementations2 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.


On the Fairness of Time-Critical Influence Maximization in Social Networks

no code implementations16 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

On the Long-term Impact of Algorithmic Decision Policies: Effort Unfairness and Feature Segregation through Social Learning

1 code implementation4 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.

Decision Making Fairness +1

Fighting Fire with Fire: Using Antidote Data to Improve Polarization and Fairness of Recommender Systems

1 code implementation2 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.

Fairness Recommendation Systems

A Moral Framework for Understanding of Fair ML through Economic Models of Equality of Opportunity

no code implementations10 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.

Fairness Philosophy

A Unified Approach to Quantifying Algorithmic Unfairness: Measuring Individual & Group Unfairness via Inequality Indices

no code implementations2 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.

Decision Making Fairness

Fairness Behind a Veil of Ignorance: A Welfare Analysis for Automated Decision Making

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.

Decision Making Fairness

Blind Justice: Fairness with Encrypted Sensitive Attributes

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.


iFair: Learning Individually Fair Data Representations for Algorithmic Decision Making

no code implementations4 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.

Decision Making Fairness +1

Equity of Attention: Amortizing Individual Fairness in Rankings

no code implementations4 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.

Fairness Recommendation Systems

Human Perceptions of Fairness in Algorithmic Decision Making: A Case Study of Criminal Risk Prediction

no code implementations26 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.

Decision Making Fairness

From Parity to Preference-based Notions of Fairness in Classification

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.

Classification Decision Making +2

On Fairness, Diversity and Randomness in Algorithmic Decision Making

no code implementations30 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.

Decision Making Fairness

The Case for Temporal Transparency: Detecting Policy Change Events in Black-Box Decision Making Systems

no code implementations31 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.

Decision Making Time Series +1

Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment

3 code implementations26 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.

Decision Making Fairness +1

Fairness Constraints: Mechanisms for Fair Classification

2 code implementations19 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.

Classification Decision Making +2

Cannot find the paper you are looking for? You can Submit a new open access paper.