Reza Khanmohammadi, Erfan Miahi, Mehrsa Mardikoraem, Simerjot Kaur, Ivan Brugere, Charese Smiley, Kundan S Thind, Mohammad M. Ghassemi. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Machine unlearning offers a practical alternative to avoid full model re-training by approximately removing the influence of specific user data. While existing methods certify unlearning via statistical indistinguishability from re-trained models, these guarantees do not naturally extend to model outputs when inputs are adversarially perturbed. In particular, slight perturbations of forget samples may still be correctly recognized by the unlearned model---even when a re-trained model fails to do so---revealing a novel privacy risk: information about the forget samples may persist in their local neighborhood. In this work, we formalize this vulnerability as residual knowledge and show that it is inevitable in high-dimensional settings. To mitigate this risk, we propose a fine-tuning strategy, named RURK, that penalizes the model’s ability to re-recognize perturbed forget samples. Experiments on vision benchmarks with deep neural networks demonstrate that residual knowledge is prevalent across existing unlearning methods and that our approach effectively prevents residual knowledge.

Models for natural language and images benefit from data scaling behavior: the more data fed into the model, the better they perform. This 'better with more' phenomenon enables the effectiveness of large-scale pre-training on vast amounts of data. However, current graph pre-training methods struggle to scale up data due to heterogeneity across graphs. To achieve effective data scaling, we aim to develop a general model that is able to capture diverse data patterns of graphs and can be utilized to adaptively help the downstream tasks. To this end, we propose UniAug, a universal graph structure augmentor built on a diffusion model. We first pre-train a discrete diffusion model on thousands of graphs across domains to learn the graph structural patterns. In the downstream phase, we provide adaptive enhancement by conducting graph structure augmentation with the help of the pre-trained diffusion model via guided generation. By leveraging the pre-trained diffusion model for structure augmentation, we consistently achieve performance improvements across various downstream tasks in a plug-and-play manner. To the best of our knowledge, this study represents the first demonstration of a data-scaling graph structure augmentor on graphs across domains.

The relationship between scientific innovation in biomedical sciences and its impact on industrial activities is a complex and dynamic process. This article investigates the relationship between science and industrial innovation, focusing on how the historical impact and content of scientific paper abstracts are associated with future funding and innovation grant application content for small businesses. The research incorporates bibliometric analyses along with small business innovation research (SBIR) data to yield a holistic view of the science-industry interface. We quantify the temporal effects and impact latency of scientific advancements on industrial activity across 10873 topics and take into account their taxonomic relationships, spanning from 2010 to 2021. We find that the impact of scientific advances on industrial projects across different thematic depths consistently exhibitedp-values less than 0.05, underscoring the significant predictive power of contemporary scientific activities on future industrial projects. Further, we demonstrate that the semantic contents of scientific paper abstracts within a topic are associated with future industrial project description text embeddings. The frequency analysis reveals that various scientific activities significantly inform future industrial project funding across varying depths of MeSH topic categorization, highlighting the significant role of science in steering industrial innovation. This study demonstrates that the impact of scientific research on industrial innovation extends beyond the mere volume of scientific output, but is greatly influenced by its impact, the broader themes it advances, and the meaningful narratives it presents.

Fair decision-making in Machine Learning (ML) remains a critical challenge, particularly when access to sensitive information is restricted due to legal, ethical, or organizational constraints. These limitations affect both accuracy and fairness, creating tradeoffs central to the deployment of ML systems in the real world. While prior work has studied fairness-accuracy tradeoffs, most approaches focus on model outputs rather than directly examining how restricted data access impacts fairness. This leaves an important gap: understanding how fairness constraints affect model performance under real-world data restrictions . To address this gap, we propose a framework that explicitly models fairness-accuracy tradeoffs in data-restricted environments. Unlike prior work, our approach analyzes the behavior of the optimal Bayesian classifier using a discrete approximation of the data distribution, allowing us to systematically isolate the effects of fairness constraints. We evaluate our framework on three benchmark datasets—Adult, Law, and Dutch Census—revealing key insights: (1) enforcing equal accuracy on imbalanced datasets can substantially degrade performance under additional fairness constraints, (2) individual and group fairness often impose conflicting constraints, and (3) decorrelating sensitive attributes from features does not usually reduce accuracy. These findings demonstrate that our framework provides an effective, structured approach for practitioners to assess fairness constraints in decision-making pipelines.

The growing use of machine learning (ML) has raised concerns that an ML model may reveal private information about an individual who has contributed to the training dataset. To prevent leakage of sensitive data, we consider using differentially- private (DP), synthetic training data instead of real training data to train an ML model. A key desirable property of synthetic data is its ability to preserve the low-order marginals of the original distribution. Our main contribution comprises novel upper and lower bounds on the excess empirical risk of linear models trained on such synthetic data, for continuous and Lipschitz loss functions. We perform extensive experimentation alongside our theoretical results.

The Rashomon effect is a mixed blessing in responsible machine learning. It enhances the prospects of finding models that perform well in accuracy while adhering to ethical standards, such as fairness or interpretability. Conversely, it poses a risk to the credibility of machine decisions through predictive multiplicity. While recent studies have explored the Rashomon effect across various machine learning algorithms, its impact on gradient boosting---an algorithm widely applied to tabular datasets---remains unclear. This paper addresses this gap by systematically analyzing the Rashomon effect and predictive multiplicity in gradient boosting algorithms. We provide rigorous theoretical derivations to examine the Rashomon effect in the context of gradient boosting and offer an information-theoretic characterization of the Rashomon set. Additionally, we introduce a novel inference technique called RashomonGB to efficiently inspect the Rashomon effect in practice. On more than 20 datasets, our empirical results show that RashomonGB outperforms existing baselines in terms of improving the estimation of predictive multiplicity metrics and model selection with group fairness constraints. Lastly, we propose a framework to mitigate predictive multiplicity in gradient boosting and empirically demonstrate its effectiveness.

Increases in the deployment of machine learning algorithms for applications that deal with sensitive data have brought attention to the issue of fairness in machine learning. Many works have been devoted to applications that require different demographic groups to be treated fairly. However, algorithms that aim to satisfy inter-group fairness (also called group fairness) may inadvertently treat individuals within the same demographic group unfairly. To address this issue, this article introduces a formal definition of within-group fairness that maintains fairness among individuals from within the same group. A pre-processing framework is proposed to meet both inter- and within-group fairness criteria with little compromise in performance. The framework maps the feature vectors of members from different groups to an inter-group fair canonical domain before feeding them into a scoring function. The mapping is constructed to preserve the relative relationship between the scores obtained from the unprocessed feature vectors of individuals from the same demographic group, guaranteeing within-group fairness. This framework has been applied to the Adult, COMPAS risk assessment, and Law School datasets, and its performance is demonstrated and compared with two regularization-based methods in achieving inter-group and within-group fairness.

Similarity functions measure how comparable pairs of elements are, and play a key role in a wide variety of applications, e.g., notions of Individual Fairness abiding by the seminal paradigm of Dwork et al., as well as Clustering problems. However, access to an accurate similarity function should not always be considered guaranteed, and this point was even raised by Dwork et al. For instance, it is reasonable to assume that when the elements to be compared are produced by different distributions, or in other words belong to different ``demographic'' groups, knowledge of their true similarity might be very difficult to obtain. In this work, we present an efficient sampling framework that learns these across-groups similarity functions, using only a limited amount of experts' feedback. We show analytical results with rigorous theoretical bounds, and empirically validate our algorithms via a large suite of experiments.

OBJECTIVE: Applications of machine learning in healthcare are of high interest and have the potential to improve patient care. Yet, the real-world accuracy of these models in clinical practice and on different patient subpopulations remains unclear. To address these important questions, we hosted a community challenge to evaluate methods that predict healthcare outcomes. We focused on the prediction of all-cause mortality as the community challenge question. MATERIALS AND METHODS: Using a Model-to-Data framework, 345 registered participants, coalescing into 25 independent teams, spread over 3 continents and 10 countries, generated 25 accurate models all trained on a dataset of over 1.1 million patients and evaluated on patients prospectively collected over a 1-year observation of a large health system. RESULTS: The top performing team achieved a final area under the receiver operator curve of 0.947 (95% CI, 0.942-0.951) and an area under the precision-recall curve of 0.487 (95% CI, 0.458-0.499) on a prospectively collected patient cohort. DISCUSSION: Post hoc analysis after the challenge revealed that models differ in accuracy on subpopulations, delineated by race or gender, even when they are trained on the same data. CONCLUSION: This is the largest community challenge focused on the evaluation of state-of-the-art machine learning methods in a healthcare system performed to date, revealing both opportunities and pitfalls of clinical AI.

Disparate access to resources by different subpopulations is a prevalent issue in societal and sociotechnical networks. For example, urban infrastructure networks may enable certain racial groups to more easily access resources such as high-quality schools, grocery stores, and polling places. Similarly, social networks within universities and organizations may enable certain groups to more easily access people with valuable information or influence. Here we introduce a new class of problems, Graph Augmentation for Equitable Access (GAEA), to enhance equity in networked systems by editing graph edges under budget constraints. We prove such problems are NP-hard, and cannot be approximated within a factor of (1-1/3e). We develop a principled, sample- and time- efficient Markov Reward Process (MRP)-based mechanism design framework for GAEA. Our algorithm outperforms baselines on a diverse set of synthetic graphs. We further demonstrate the method on real-world networks, by merging public census, school, and transportation datasets for the city of Chicago and applying our algorithm to find human-interpretable edits to the bus network that enhance equitable access to high-quality schools across racial groups. Further experiments on Facebook networks of universities yield sets of new social connections that would increase equitable access to certain attributed nodes across gender groups.

Behavior initiation is a form of leadership and is an important aspect of social organization that affects the processes of group formation, dynamics, and decision-making in human societies and other social animal species. In this work, we formalize the C oordination I nitiator I nference P roblem and propose a simple yet powerful framework for extracting periods of coordinated activity and determining individuals who initiated this coordination, based solely on the activity of individuals within a group during those periods. The proposed approach, given arbitrary individual time series, automatically (1) identifies times of coordinated group activity, (2) determines the identities of initiators of those activities, and (3) classifies the likely mechanism by which the group coordination occurred, all of which are novel computational tasks. We demonstrate our framework on both simulated and real-world data: trajectories tracking of animals as well as stock market data. Our method is competitive with existing global leadership inference methods but provides the first approaches for local leadership and coordination mechanism classification. Our results are consistent with ground-truthed biological data and the framework finds many known events in financial data which are not otherwise reflected in the aggregate NASDAQ index. Our method is easily generalizable to any coordinated time series data from interacting entities.

GOPHER (Global Observation of Planetary Health and Ecosystem Resources) is a collection of data mining algorithms for detecting global land use and land cover change that builds on a decade of research on spatio temporal data mining at the University of Minnesota; the GOPHER approach to analyzing remote sensing imagery provides such a solution by providing rapid, inexpensive, robust, scalable, and precise detection of land use change. GOPHER algorithms are able to detect historical changes with high precision, and more recent changes with reasonable precision in as little as 8 weeks after changes occur (this is due to a combination of remote sensing data availability and modeling needs). This paper outlines the GOPHER approach and provides some illustrative results to demonstrate its utility.