FairEM360: A Suite for Responsible Entity Matching

Entity matching is one the earliest tasks that occur in the big data pipeline and is alarmingly exposed to unintentional biases that affect the quality of data. Identifying and mitigating the biases that exist in the data or are introduced by the matcher at this stage can contribute to promoting fairness in downstream tasks. This demonstration showcases FairEM360, a framework for 1) auditing the output of entity matchers across a wide range of fairness measures and paradigms, 2) providing potential explanations for the underlying reasons for unfairness, and 3) providing resolutions for the unfairness issues through an exploratory process with human-in-the-loop feedback, utilizing an ensemble of matchers. We aspire for FairEM360 to contribute to the prioritization of fairness as a key consideration in the evaluation of EM pipelines.

AXOLOTL: Fairness through Assisted Self-Debiasing of Large Language Model Outputs

Pre-trained Large Language Models (LLMs) have significantly advanced natural language processing capabilities but are susceptible to biases present in their training data, leading to unfair outcomes in various applications. While numerous strategies have been proposed to mitigate bias, they often require extensive computational resources and may compromise model performance. In this work, we introduce AXOLOTL, a novel post-processing framework, which operates agnostically across tasks and models, leveraging public APIs to interact with LLMs without direct access to internal parameters. Through a three-step process resembling zero-shot learning, AXOLOTL identifies biases, proposes resolutions, and guides the model to self-debias its outputs. This approach minimizes computational costs and preserves model performance, making AXOLOTL a promising tool for debiasing LLM outputs with broad applicability and ease of use.

Chameleon: Foundation Models for Fairness-aware Multi-modal Data Augmentation to Enhance Coverage of Minorities

The potential harms of the under-representation of minorities in training data, particularly in multi-modal settings, is a well-recognized concern. While there has been extensive effort in detecting such under-representation, resolution has remained a challenge. With recent advancements in generative AI, large language models and foundation models have emerged as versatile tools across various domains. In this paper, we propose Chameleon, a system that efficiently utilizes these tools to augment a data set with a minimal addition of synthetically generated tuples, in order to enhance the coverage of the under-represented groups. Our system follows a rejection sampling approach to ensure the generated tuples have a high quality and follow the underlying distribution. In order to minimize the rejection chance of the generated tuples, we propose multiple strategies for providing a guide for the foundation model. Our experiment results, in addition to confirming the efficiency of our proposed algorithms, illustrate the effectiveness of our approach, as the unfairness of the model in a downstream task significantly dropped after data repair using Chameleon.

Efficient Strongly Polynomial Algorithms for Quantile Regression

Linear Regression is a seminal technique in statistics and machine learning, where the objective is to build linear predictive models between a response (i.e., dependent) variable and one or more predictor (i.e., independent) variables. In this paper, we revisit the classical technique of Quantile Regression (QR), which is statistically a more robust alternative to the other classical technique of Ordinary Least Square Regression (OLS). However, while there exist efficient algorithms for OLS, almost all of the known results for QR are only weakly polynomial. Towards filling this gap, this paper proposes several efficient strongly polynomial algorithms for QR for various settings. For two dimensional QR, making a connection to the geometric concept of $k$-set, we propose an algorithm with a deterministic worst-case time complexity of $\mathcal{O}(n^{4/3} polylog(n))$ and an expected time complexity of $\mathcal{O}(n^{4/3})$ for the randomized version. We also propose a randomized divide-and-conquer algorithm -- RandomizedQR with an expected time complexity of $\mathcal{O}(n\log^2{(n)})$ for two dimensional QR problem. For the general case with more than two dimensions, our RandomizedQR algorithm has an expected time complexity of $\mathcal{O}(n^{d-1}\log^2{(n)})$.

Through the Fairness Lens: Experimental Analysis and Evaluation of Entity Matching

Entity matching (EM) is a challenging problem studied by different communities for over half a century. Algorithmic fairness has also become a timely topic to address machine bias and its societal impacts. Despite extensive research on these two topics, little attention has been paid to the fairness of entity matching. Towards addressing this gap, we perform an extensive experimental evaluation of a variety of EM techniques in this paper. We generated two social datasets from publicly available datasets for the purpose of auditing EM through the lens of fairness. Our findings underscore potential unfairness under two common conditions in real-world societies: (i) when some demographic groups are overrepresented, and (ii) when names are more similar in some groups compared to others. Among our many findings, it is noteworthy to mention that while various fairness definitions are valuable for different settings, due to EM's class imbalance nature, measures such as positive predictive value parity and true positive rate parity are, in general, more capable of revealing EM unfairness.

Sampling-Based Techniques for Training Deep Neural Networks with Limited Computational Resources: A Scalability Evaluation

Deep neural networks are superior to shallow networks in learning complex representations. As such, there is a fast-growing interest in utilizing them in large-scale settings. The training process of neural networks is already known to be time-consuming, and having a deep architecture only aggravates the issue. This process consists mostly of matrix operations, among which matrix multiplication is the bottleneck. Several sampling-based techniques have been proposed for speeding up the training time of deep neural networks by approximating the matrix products. These techniques fall under two categories: (i) sampling a subset of nodes in every hidden layer as active at every iteration and (ii) sampling a subset of nodes from the previous layer to approximate the current layer's activations using the edges from the sampled nodes. In both cases, the matrix products are computed using only the selected samples. In this paper, we evaluate the scalability of these approaches on CPU machines with limited computational resources. Making a connection between the two research directions as special cases of approximating matrix multiplications in the context of neural networks, we provide a negative theoretical analysis that shows feedforward approximation is an obstacle against scalability. We conduct comprehensive experimental evaluations that demonstrate the most pressing challenges and limitations associated with the studied approaches. We observe that the hashing-based node selection method is not scalable to a large number of layers, confirming our theoretical analysis. Finally, we identify directions for future research.

FairPilot: An Explorative System for Hyperparameter Tuning through the Lens of Fairness

Despite the potential benefits of machine learning (ML) in high-risk decision-making domains, the deployment of ML is not accessible to practitioners, and there is a risk of discrimination. To establish trust and acceptance of ML in such domains, democratizing ML tools and fairness consideration are crucial. In this paper, we introduce FairPilot, an interactive system designed to promote the responsible development of ML models by exploring a combination of various models, different hyperparameters, and a wide range of fairness definitions. We emphasize the challenge of selecting the ``best" ML model and demonstrate how FairPilot allows users to select a set of evaluation criteria and then displays the Pareto frontier of models and hyperparameters as an interactive map. FairPilot is the first system to combine these features, offering a unique opportunity for users to responsibly choose their model.

A Survey on Techniques for Identifying and Resolving Representation Bias in Data

The grand goal of data-driven decision-making is to help humans make decisions, not only easily and at scale but also wisely, accurately, and just. However, data-driven algorithms are only as good as the data they work with, while data sets, especially social data, often miss representing minorities. Representation Bias in data can happen due to various reasons ranging from historical discrimination to selection and sampling biases in the data acquisition and preparation methods. One cannot expect AI-based societal solutions to have equitable outcomes without addressing the representation bias. This paper surveys the existing literature on representation bias in the data. It presents a taxonomy to categorize the studied techniques based on multiple design dimensions and provide a side-by-side comparison of their properties. There is still a long way to fully address representation bias issues in data. The authors hope that this survey motivates researchers to approach these challenges in the future by observing existing work within their respective domains.

On the Choice of Fairness: Finding Representative Fairness Metrics for a Given Context

It is of critical importance to be aware of the historical discrimination embedded in the data and to consider a fairness measure to reduce bias throughout the predictive modeling pipeline. Various notions of fairness have been defined, though choosing an appropriate metric is cumbersome. Trade-offs and impossibility theorems make such selection even more complicated and controversial. In practice, users (perhaps regular data scientists) should understand each of the measures and (if possible) manually explore the combinatorial space of different measures before they can decide which combination is preferred based on the context, the use case, and regulations. To alleviate the burden of selecting fairness notions for consideration, we propose a framework that automatically discovers the correlations and trade-offs between different pairs of measures for a given context. Our framework dramatically reduces the exploration space by finding a small subset of measures that represent others and highlighting the trade-offs between them. This allows users to view unfairness from various perspectives that might otherwise be ignored due to the sheer size of the exploration space. We showcase the validity of the proposal using comprehensive experiments on real-world benchmark data sets.

OmniFair: A Declarative System for Model-Agnostic Group Fairness in Machine Learning

Machine learning (ML) is increasingly being used to make decisions in our society. ML models, however, can be unfair to certain demographic groups (e.g., African Americans or females) according to various fairness metrics. Existing techniques for producing fair ML models either are limited to the type of fairness constraints they can handle (e.g., preprocessing) or require nontrivial modifications to downstream ML training algorithms (e.g., in-processing). We propose a declarative system OmniFair for supporting group fairness in ML. OmniFair features a declarative interface for users to specify desired group fairness constraints and supports all commonly used group fairness notions, including statistical parity, equalized odds, and predictive parity. OmniFair is also model-agnostic in the sense that it does not require modifications to a chosen ML algorithm. OmniFair also supports enforcing multiple user declared fairness constraints simultaneously while most previous techniques cannot. The algorithms in OmniFair maximize model accuracy while meeting the specified fairness constraints, and their efficiency is optimized based on the theoretically provable monotonicity property regarding the trade-off between accuracy and fairness that is unique to our system. We conduct experiments on commonly used datasets that exhibit bias against minority groups in the fairness literature. We show that OmniFair is more versatile than existing algorithmic fairness approaches in terms of both supported fairness constraints and downstream ML models. OmniFair reduces the accuracy loss by up to $94.8\%$ compared with the second best method. OmniFair also achieves similar running time to preprocessing methods, and is up to $270\times$ faster than in-processing methods.