arXiv subjects

Abolfazl Asudeh

Publications and source records attributed to Abolfazl Asudeh.

At least 37 records · Page 2Linked to original sources

arXiv2024

Rank It, Then Ask It: Input Reranking for Maximizing the Performance of LLMs on Symmetric Tasks

Large language models (LLMs) have quickly emerged as practical and versatile tools that provide new solutions for a wide range of domains. In this paper, we consider the application of LLMs on symmetric tasks where a query is asked on an (unordered) bag of elements. Examples of such tasks include answering aggregate queries on a database table. In general, when the bag contains a large number of elements, LLMs tend to overlook some elements, leading to challenges in generating accurate responses to the query. LLMs receive their inputs as ordered sequences. However, in this problem, we leverage the fact that the symmetric input is not ordered, and reordering should not affect the LLM's response. Observing that LLMs are less likely to miss elements at certain positions of the input, we introduce the problem of LLM input reranking: to find a ranking of the input that maximizes the LLM's accuracy for the given query without making explicit assumptions about the query. Finding the optimal ranking requires identifying (i) the relevance of each input element for answering the query and (ii) the importance of each rank position for the LLM's attention. We develop algorithms for estimating these values efficiently utilizing a helper LLM. We conduct comprehensive experiments on different synthetic and real datasets to validate our proposal and to evaluate the effectiveness of our proposed algorithms. Our experiments confirm that our reranking approach improves the accuracy of the LLMs on symmetric tasks by up to $99\%$ proximity to the optimum upper bound.

cs.LG↗

arXiv2024

Online Maximum Independent Set of Hyperrectangles

The maximum independent set problem is a classical NP-hard problem in theoretical computer science. In this work, we study a special case where the family of graphs considered is restricted to intersection graphs of sets of axis-aligned hyperrectangles and the input is provided in an online fashion. We prove results for several adversary models, classes of hyperrectangles, and restrictions on the order of the input. Under the adaptive offline and adaptive online adversary models, we find the optimal online algorithm for unit hypercubes, $σ$-bounded hypercubes, unit-volume hyperrectangles, and arbitrary hypercubes, in both non-dominated and arbitrary order. Under the oblivious adversary model, we prove bounds on the competitive ratio of an optimal online algorithm for the same classes of hyperrectangles and input orders, and we find algorithms that are optimal up to constant factors. For input in dominating order, we find the optimal online algorithm for arbitrary hyperrectangles under all adversary models. We conclude by discussing several promising directions for future work.

cs.DS↗

arXiv2024

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.

cs.DB↗

arXiv2024

[Experiments & Analysis] Evaluating the Feasibility of Sampling-Based Techniques for Training Multilayer Perceptrons

The training process of neural networks is 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 feasibility 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.

cs.LG↗

arXiv2024

REQUAL-LM: Reliability and Equity through Aggregation in Large Language Models

The extensive scope of large language models (LLMs) across various domains underscores the critical importance of responsibility in their application, beyond natural language processing. In particular, the randomized nature of LLMs, coupled with inherent biases and historical stereotypes in data, raises critical concerns regarding reliability and equity. Addressing these challenges are necessary before using LLMs for applications with societal impact. Towards addressing this gap, we introduce REQUAL-LM, a novel method for finding reliable and equitable LLM outputs through aggregation. Specifically, we develop a Monte Carlo method based on repeated sampling to find a reliable output close to the mean of the underlying distribution of possible outputs. We formally define the terms such as reliability and bias, and design an equity-aware aggregation to minimize harmful bias while finding a highly reliable output. REQUAL-LM does not require specialized hardware, does not impose a significant computing load, and uses LLMs as a blackbox. This design choice enables seamless scalability alongside the rapid advancement of LLM technologies. Our system does not require retraining the LLMs, which makes it deployment ready and easy to adapt. Our comprehensive experiments using various tasks and datasets demonstrate that REQUAL- LM effectively mitigates bias and selects a more equitable response, specifically the outputs that properly represents minority groups.

cs.CL↗

arXiv2024

A Fair and Memory/Time-efficient Hashmap

Hashmap is a fundamental data structure in computer science. There has been extensive research on constructing hashmaps that minimize the number of collisions leading to efficient lookup query time. Recently, the data-dependant approaches, construct hashmaps tailored for a target data distribution that guarantee to uniformly distribute data across different buckets and hence minimize the collisions. Still, to the best of our knowledge, none of the existing technique guarantees group fairness among different groups of items stored in the hashmap. Therefore, in this paper, we introduce FairHash, a data-dependant hashmap that guarantees uniform distribution at the group-level across hash buckets, and hence, satisfies the statistical parity notion of group fairness. We formally define, three notions of fairness and, unlike existing work, FairHash satisfies all three of them simultaneously. We propose three families of algorithms to design fair hashmaps, suitable for different settings. Our ranking-based algorithms reduce the unfairness of data-dependant hashmaps without any memory-overhead. The cut-based algorithms guarantee zero-unfairness in all cases, irrespective of how the data is distributed, but those introduce an extra memory-overhead. Last but not least, the discrepancy-based algorithms enable trading off between various fairness notions. In addition to the theoretical analysis, we perform extensive experiments to evaluate the efficiency and efficacy of our algorithms on real datasets. Our results verify the superiority of FairHash compared to the other baselines on fairness at almost no performance cost.

cs.DS↗

arXiv2024

Reliability Evaluation of Individual Predictions: A Data-centric Approach

Machine learning models only provide probabilistic guarantees on the expected loss of random samples from the distribution represented by their training data. As a result, a model with high accuracy, may or may not be reliable for predicting an individual query point. To address this issue, XAI aims to provide explanations of individual predictions, while approaches such as conformal predictions, probabilistic predictions, and prediction intervals count on the model's certainty in its prediction to identify unreliable cases. Conversely, instead of relying on the model itself, we look for insights in the training data. That is, following the fact a model's performance is limited to the data it has been trained on, we ask "is a model trained on a given data set, fit for making a specific prediction?". Specifically, we argue that a model's prediction is not reliable if (i) there were not enough similar instances in the training set to the query point, and (ii) if there is a high fluctuation (uncertainty) in the vicinity of the query point in the training set. Using these two observations, we propose data-centric reliability measures for individual predictions and develop novel algorithms for efficient and effective computation of the reliability measures during inference time. The proposed algorithms learn the necessary components of the measures from the data itself and are sublinear, which makes them scalable to very large and multi-dimensional settings. Furthermore, an estimator is designed to enable no-data access during the inference time. We conduct extensive experiments using multiple real and synthetic data sets and different tasks, which reflect a consistent correlation between distrust values and model performance.

cs.DB↗

arXiv2024

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.

cs.CL↗

arXiv2024

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.

cs.LG↗

arXiv2023

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 $\mathcal{O}(n^{d-1}\log^2{(n)})$.

cs.CG↗

arXiv2023

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.

cs.DB↗

arXiv2023

Data Coverage for Detecting Representation Bias in Image Datasets: A Crowdsourcing Approach

Existing machine learning models have proven to fail when it comes to their performance for minority groups, mainly due to biases in data. In particular, datasets, especially social data, are often not representative of minorities. In this paper, we consider the problem of representation bias identification on image datasets without explicit attribute values. Using the notion of data coverage for detecting a lack of representation, we develop multiple crowdsourcing approaches. Our core approach, at a high level, is a divide and conquer algorithm that applies a search space pruning strategy to efficiently identify if a dataset misses proper coverage for a given group. We provide a different theoretical analysis of our algorithm, including a tight upper bound on its performance which guarantees its near-optimality. Using this algorithm as the core, we propose multiple heuristics to reduce the coverage detection cost across different cases with multiple intersectional/non-intersectional groups. We demonstrate how the pre-trained predictors are not reliable and hence not sufficient for detecting representation bias in the data. Finally, we adjust our core algorithm to utilize existing models for predicting image group(s) to minimize the coverage identification cost. We conduct extensive experiments, including live experiments on Amazon Mechanical Turk to validate our problem and evaluate our algorithms' performance.

cs.DB↗

arXiv2023

Maximizing Neutrality in News Ordering

The detection of fake news has received increasing attention over the past few years, but there are more subtle ways of deceiving one's audience. In addition to the content of news stories, their presentation can also be made misleading or biased. In this work, we study the impact of the ordering of news stories on audience perception. We introduce the problems of detecting cherry-picked news orderings and maximizing neutrality in news orderings. We prove hardness results and present several algorithms for approximately solving these problems. Furthermore, we provide extensive experimental results and present evidence of potential cherry-picking in the real world.

cs.DS↗

arXiv2023

PopSim: An Individual-level Population Simulator for Equitable Allocation of City Resources

Historical systematic exclusionary tactics based on race have forced people of certain demographic groups to congregate in specific urban areas. Aside from the ethical aspects of such segregation, these policies have implications for the allocation of urban resources including public transportation, healthcare, and education within the cities. The initial step towards addressing these issues involves conducting an audit to assess the status of equitable resource allocation. However, due to privacy and confidentiality concerns, individual-level data containing demographic information cannot be made publicly available. By leveraging publicly available aggregated demographic statistics data, we introduce PopSim, a system for generating semi-synthetic individual-level population data with demographic information. We use PopSim to generate multiple benchmark datasets for the city of Chicago and conduct extensive statistical evaluations to validate those. We further use our datasets for several case studies that showcase the application of our system for auditing equitable allocation of city resources.

cs.CY↗

arXiv2023

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.

cs.LG↗

arXiv2023

Representation Bias in Data: A Survey on Identification and Resolution Techniques

Data-driven algorithms are only as good as the data they work with, while data sets, especially social data, often fail to represent minorities adequately. 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. Given that "bias in, bias out", one cannot expect AI-based solutions to have equitable outcomes for societal applications, without addressing issues such as representation bias. While there has been extensive study of fairness in machine learning models, including several review papers, bias in the data has been less studied. This paper reviews the literature on identifying and resolving representation bias as a feature of a data set, independent of how consumed later. The scope of this survey is bounded to structured (tabular) and unstructured (e.g., image, text, graph) data. It presents taxonomies to categorize the studied techniques based on multiple design dimensions and provides 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.

cs.DB↗

arXiv2022

Finding Representative Group Fairness Metrics Using Correlation Estimations

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. Given various notions of fairness defined in the literature, investigating the correlation and interaction among metrics is vital for addressing unfairness. Practitioners and data scientists should be able to comprehend each metric and examine their impact on one another given the context, use case, and regulations. Exploring the combinatorial space of different metrics for such examination is burdensome. To alleviate the burden of selecting fairness notions for consideration, we propose a framework that estimates the correlation among fairness notions. Our framework consequently identifies a set of diverse and semantically distinct metrics as representative for a given context. We propose a Monte-Carlo sampling technique for computing the correlations between fairness metrics by indirect and efficient perturbation in the model space. Using the estimated correlations, we then find a subset of representative metrics. The paper proposes a generic method that can be generalized to any arbitrary set of fairness metrics. We showcase the validity of the proposal using comprehensive experiments on real-world benchmark datasets.

cs.LG↗

arXiv2022

Maximizing Fair Content Spread via Edge Suggestion in Social Networks

Content spread inequity is a potential unfairness issue in online social networks, disparately impacting minority groups. In this paper, we view friendship suggestion, a common feature in social network platforms, as an opportunity to achieve an equitable spread of content. In particular, we propose to suggest a subset of potential edges (currently not existing in the network but likely to be accepted) that maximizes content spread while achieving fairness. Instead of re-engineering the existing systems, our proposal builds a fairness wrapper on top of the existing friendship suggestion components. We prove the problem is NP-hard and inapproximable in polynomial time unless P = NP. Therefore, allowing relaxation of the fairness constraint, we propose an algorithm based on LP-relaxation and randomized rounding with fixed approximation ratios on fairness and content spread. We provide multiple optimizations, further improving the performance of our algorithm in practice. Besides, we propose a scalable algorithm that dynamically adds subsets of nodes, chosen via iterative sampling, and solves smaller problems corresponding to these nodes. Besides theoretical analysis, we conduct comprehensive experiments on real and synthetic data sets. Across different settings, our algorithms found solutions with nearzero unfairness while significantly increasing the content spread. Our scalable algorithm could process a graph with half a million nodes on a single machine, reducing the unfairness to around 0.0004 while lifting content spread by 43%.

cs.SI↗