Search Results for author:
Found 39 papers, 15 papers with code
Towards Reliable Latent Knowledge Estimation in LLMs: In-Context Learning vs. Prompting Based Factual Knowledge Extraction
We propose an approach for estimating the latent knowledge embedded inside large language models (LLMs).
Antitrust, Amazon, and Algorithmic Auditing
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
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
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
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.
Scheduling Virtual Conferences Fairly: Achieving Equitable Participant and Speaker Satisfaction
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.
FaiRIR: Mitigating Exposure Bias from Related Item Recommendations in Two-Sided Platforms
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
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
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.
On Fair Selection in the Presence of Implicit and Differential Variance
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.
Do Invariances in Deep Neural Networks Align with Human Perception?
One necessary criterion for a network's invariances to align with human perception is for its IRIs look 'similar' to humans.
Detecting and Mitigating Test-time Failure Risks via Model-agnostic Uncertainty Learning
Reliably predicting potential failure risks of machine learning (ML) systems when deployed with production data is a crucial aspect of trustworthy AI.
Loss-Aversively Fair Classification
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.
Accounting for Model Uncertainty in Algorithmic Discrimination
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.
CrossWalk: Fairness-enhanced Node Representation Learning
The potential for machine learning systems to amplify social inequities and unfairness is receiving increasing popular and academic attention.
When the Umpire is also a Player: Bias in Private Label Product Recommendations on E-commerce Marketplaces
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
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.
Unifying Model Explainability and Robustness via Machine-Checkable Concepts
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
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
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.
FairRec: Two-Sided Fairness for Personalized Recommendations in Two-Sided Platforms
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.
DADI: Dynamic Discovery of Fair Information with Adversarial Reinforcement Learning
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.
An Empirical Study on Learning Fairness Metrics for COMPAS Data with Human Supervision
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.
Operationalizing Individual Fairness with Pairwise Fair Representations
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
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
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.
Fighting Fire with Fire: Using Antidote Data to Improve Polarization and Fairness of Recommender Systems
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.
A Moral Framework for Understanding of Fair ML through Economic Models of Equality of Opportunity
In this respect, our work serves as a unifying moral framework for understanding existing notions of algorithmic fairness.
A Unified Approach to Quantifying Algorithmic Unfairness: Measuring Individual & Group Unfairness via Inequality Indices
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.
Fairness Behind a Veil of Ignorance: A Welfare Analysis for Automated Decision Making
We draw attention to an important, yet largely overlooked aspect of evaluating fairness for automated decision making systems---namely risk and welfare considerations.
Blind Justice: Fairness with Encrypted Sensitive Attributes
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
We demonstrate the versatility of our method by applying it to classification and learning-to-rank tasks on a variety of real-world datasets.
Equity of Attention: Amortizing Individual Fairness in Rankings
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.
Human Perceptions of Fairness in Algorithmic Decision Making: A Case Study of Criminal Risk Prediction
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.
From Parity to Preference-based Notions of Fairness in Classification
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.
On Fairness, Diversity and Randomness in Algorithmic Decision Making
Consider a binary decision making process where a single machine learning classifier replaces a multitude of humans.
The Case for Temporal Transparency: Detecting Policy Change Events in Black-Box Decision Making Systems
Bringing transparency to black-box decision making systems (DMS) has been a topic of increasing research interest in recent years.
Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment
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.
Fairness Constraints: Mechanisms for Fair Classification
Algorithmic decision making systems are ubiquitous across a wide variety of online as well as offline services.
