Foundation models for tabular data, such as the Tabular Prior-data Fitted Network (TabPFN), are pre-trained on a massive number of synthetic datasets generated by structural causal models (SCM). They leverage in-context learning to offer high predictive accuracy in real-world tasks. However, the fairness properties of these foundational models, which incorporate ideas from causal reasoning during pre-training, remain underexplored. In this work, we conduct a comprehensive empirical evaluation of TabPFN and its fine-tuned variants, assessing predictive performance, fairness, and robustness across varying dataset sizes and distributional shifts. Our results reveal that while TabPFN achieves stronger predictive accuracy compared to baselines and exhibits robustness to spurious correlations, improvements in fairness are moderate and inconsistent, particularly under missing-not-at-random (MNAR) covariate shifts. These findings suggest that the causal pre-training in TabPFN is helpful but insufficient for algorithmic fairness, highlighting implications for deploying TabPFN (and similar) models in practice and the need for further fairness interventions.

Machine learning requires defining one's target variable for predictions or decisions, a process that can have profound implications on fairness, since biases are often encoded in target variable definition itself, before any data collection or training. The downstream impacts of target variable definitions must be taken into account in order to responsibly develop, deploy, and use the algorithmic systems. We propose FairTargetSim (FTS), an interactive and simulations-based approach for this. We demonstrate FTS using the example of algorithmic hiring, grounded in real-world data and user-defined target variables. FTS is open-source; it can be used by algorithm developers, non-technical stakeholders, researchers, and educators in a number of ways. FTS is available at: http://tinyurl.com/ftsinterface. The video accompanying this paper is here: http://tinyurl.com/ijcaifts.

Data and their processing have become an indispensable aspect for our society. Insights drawn from collective data make invaluable contribution to scientific, societal and communal research and business. However, there are increasing worries about privacy issues and data misuse, prompting the emergence of decentralised personal data stores (PDS) like Solid. However, existing PDS frameworks face challenges in ensuring data privacy when performing collective computation to combine data from multiple users. At a glance, Secure Multi-Party Computation (MPC) offers input secrecy protection while performing collective computation without relying on any single party. However, issues emerge when directly applying MPC in the context of PDS, particularly due to key factors like autonomy and decentralisation. In this work, we discuss the essence of this issue, identify the potential solution, and introduce a modular system architecture, Libertas, to integrate MPC with PDS like Solid, without requiring protocol-level changes. We introduce the paradigm shift from an 'omniscient' view to individual-based, user-centric view of trust and security, and discuss the threat model of Libertas. Two realistic use cases for collaborative data processing are used for evaluation, both for technical feasibility and empirical benchmark, highlighting its effectiveness in empowering gig workers and generating differentially private synthetic data. The results of our experiments underscore Libertas' linear scalability and provide valuable insights into compute optimisations, thereby advancing the state-of-the-art in privacy-preserving data processing practices. By offering practical solutions for maintaining both individual autonomy and privacy in collaborative data processing environments, Libertas contributes significantly to the ongoing discourse on privacy protection in data-driven decision-making contexts.

There is a growing body of work on learning from human feedback to align various aspects of machine learning systems with human values and preferences.We consider the setting of fairness in content moderation, in which human feedback is used to determine how two comments -referencing different sensitive attribute groups -should be treated in comparison to one another.With a novel dataset collected from Prolific and MTurk, we find significant gaps in fairness preferences depending on the race, age, political stance, educational level, and LGBTQ+ identity of annotators.We also demonstrate that demographics mentioned in text have a strong influence on how users perceive individual fairness in moderation.Further, we find that differences also exist in downstream classifiers trained to predict human preferences.Finally, we observe that an ensemble, giving equal weight to classifiers trained on annotations from different demographics, performs better for different demographic intersections; compared to a single classifier that gives equal weight to each annotation.Warning: This paper discusses examples of content that may be offensive or disturbing.

Information asymmetries create extractive, often harmful relationships between platform workers (e.g., Uber or Deliveroo drivers) and their algorithmic managers. Recent HCI studies have put forward more equitable platform designs but leave open questions about the social and technical infrastructures required to support them without the cooperation of platforms. We conducted a participatory design study in which platform workers deconstructed and re-imagined Uber’s schema for driver data. We analyzed the data structures and social institutions participants proposed, focusing on the stakeholders, roles, and strategies for mitigating conflicting interests of privacy, personal agency, and utility. Using critical theory, we reflected on the capability of participatory design to generate bottom-up collective data infrastructures. Based on the plurality of alternative institutions participants produced and their aptitude to navigate data stewardship decisions, we propose user-configurable tools for lightweight data institution building, as an alternative to redesigning existing platforms or delegating control to centralized trusts.

Machine learning based decision-support tools in criminal justice systems are subjects of intense discussions and academic research. There are important open questions about the utility and fairness of such tools. Academic researchers often rely on a few small datasets that are not sufficient to empirically study various real-world aspects of these questions. In this paper, we contribute WCLD, a curated large dataset of 1.5 million criminal cases from circuit courts in the U.S. state of Wisconsin. We used reliable public data from 1970 to 2020 to curate attributes like prior criminal counts and recidivism outcomes. The dataset contains large number of samples from five racial groups, in addition to information like sex and age (at judgment and first offense). Other attributes in this dataset include neighborhood characteristics obtained from census data, detailed types of offense, charge severity, case decisions, sentence lengths, year of filing etc. We also provide pseudo-identifiers for judge, county and zipcode. The dataset will not only enable researchers to more rigorously study algorithmic fairness in the context of criminal justice, but also relate algorithmic challenges with various systemic issues. We also discuss in detail the process of constructing the dataset and provide a datasheet. The WCLD dataset is available at https://clezdata.github.io/wcld/.

Notwithstanding the widely held view that data generation and data curation processes are prominent sources of bias in machine learning algorithms, there is little empirical research seeking to document and understand the specific data dimensions affecting algorithmic unfairness. Contra the previous work, which has focused on modeling using simple, small-scale benchmark datasets, we hold the model constant and methodically intervene on relevant dimensions of a much larger, more diverse dataset. For this purpose, we introduce a new dataset on recidivism in 1.5 million criminal cases from courts in the U.S. state of Wisconsin, 2000-2018. From this main dataset, we generate multiple auxiliary datasets to simulate different kinds of biases in the data. Focusing on algorithmic bias toward different race/ethnicity groups, we assess the relevance of training data size, base rate difference between groups, representation of groups in the training data, temporal aspects of data curation, including race/ethnicity or neighborhood characteristics as features, and training separate classifiers by race/ethnicity or crime type. We find that these factors often do influence fairness metrics holding the classifier specification constant, without having a corresponding effect on accuracy metrics. The methodology and the results in the paper provide a useful reference point for a data-centric approach to studying algorithmic fairness in recidivism prediction and beyond.

Training datasets for machine learning often have some form of missingness. For example, to learn a model for deciding whom to give a loan, the available training data includes individuals who were given a loan in the past, but not those who were not. This missingness, if ignored, nullifies any fairness guarantee of the training procedure when the model is deployed. Using causal graphs, we characterize the missingness mechanisms in different real-world scenarios. We show conditions under which various distributions, used in popular fairness algorithms, can or can not be recovered from the training data. Our theoretical results imply that many of these algorithms can not guarantee fairness in practice. Modeling missingness also helps to identify correct design principles for fair algorithms. For example, in multi-stage settings where decisions are made in multiple screening rounds, we use our framework to derive the minimal distributions required to design a fair algorithm. Our proposed algorithm also decentralizes the decision-making process and still achieves similar performance to the optimal algorithm that requires centralization and non-recoverable distributions.

We derive conditions under which a peer-consistency mechanism can be used to elicit truthful data from non-trusted rational agents when an aggregate statistic of the collected data affects the amount of their incentives to lie. Furthermore, we discuss the relative saving that can be achieved by the mechanism, compared to the rational outcome, if no such mechanism was implemented. Our work is motivated by distributed platforms, where decentralized data oracles collect information about real-world events, based on the aggregate information provided by often self-interested participants. We compare our theoretical observations with numerical simulations on two public real datasets.

Blockchain based systems allow various kinds of financial transactions to be executed in a decentralized manner. However, these systems often rely on a trusted third party (oracle) to get correct information about the real-world events, which trigger the financial transactions. In this paper, we identify two biggest challenges in building decentralized, trustless and transparent oracles. The first challenge is acquiring correct information about the real-world events without relying on a trusted information provider. We show how a peer-consistency incentive mechanism can be used to acquire truthful information from an untrusted and self-interested crowd, even when the crowd has outside incentives to provide wrong informations. The second is a system design and implementation challenge. For the first time, we show how to implement a trustless and transparent oracle in Ethereum. We discuss various non-trivial issues that arise in implementing peer-consistency mechanisms in Ethereum, suggest several optimizations to reduce gas cost and provide empirical analysis.

An important class of game-theoretic incentive mechanisms for eliciting effort from a crowd are the peer based mechanisms, in which workers are paid by matching their answers with one another. The other classic mechanism is to have the workers solve some gold standard tasks and pay them according to their accuracy on gold tasks. This mechanism ensures stronger incentive compatibility than the peer based mechanisms but assigning gold tasks to all workers becomes inefficient at large scale. We propose a novel mechanism that assigns gold tasks to only a few workers and exploits transitivity to derive accuracy of the rest of the workers from their peers’ accuracy. We show that the resulting mechanism ensures a dominant notion of incentive compatibility and fairness.

Recent studies have shown that the labels collected from crowdworkers can be discriminatory with respect to sensitive attributes such as gender and race. This raises questions about the suitability of using crowdsourced data for further use, such as for training machine learning algorithms. In this work, we address the problem of fair and diverse data collection from a crowd under budget constraints. We propose a novel algorithm which maximizes the expected accuracy of the collected data, while ensuring that the errors satisfy desired notions of fairness. We provide guarantees on the performance of our algorithm and show that the algorithm performs well in practice through experiments on a real dataset.

Biased decision making by machine learning systems is increasingly recognized as an important issue. Recently, techniques have been proposed to learn non-discriminatory clas- sifiers by enforcing constraints in the training phase. Such constraints are either non-convex in nature (posing computational difficulties) or don’t have a clear probabilistic interpretation. Moreover, the techniques offer little understanding of the more subjective notion of fairness. In this paper, we introduce a novel technique to achieve non-discrimination without sacrificing convexity and probabilistic interpretation. Our experimental analysis demonstrates the success of the method on popular real datasets including ProPublica’s COMPAS dataset. We also propose a new notion of fairness for machine learning and show that our technique satisfies this subjective fairness criterion.

We introduce a novel technique to achieve non-discrimination in machine learning without sacrificing convexity and probabilistic interpretation. We also propose a new notion of fairness for machine learning called the weighted proportional fairness and show that our technique satisfies this subjective fairness criterion.

In the Web, a massive amount of user-generated contents is available through various channels, e.g., texts, tweets, Web tables, databases, multimedia-sharing platforms, etc. Conflicting information, rumors, erroneous and fake contents can be easily spread across multiple sources, making it hard to distinguish between what is true and what is not. How do you figure out that a lie has been told often enough that it is now considered to be true? How many lying sources are required to introduce confusion in what you knew before to be the truth? To answer these questions, we present AllegatorTrack, a system that discovers true claims among conflicting data from multiple sources.