arXiv subjects

Corinna Coupette

Publications and source records attributed to Corinna Coupette.

At least 19 recordsLinked to original sources

arXiv2026

Protecting patient privacy in clinical foundation models: Technical and legal perspectives

Clinical foundation models trained on large-scale patient data are increasingly used for decision support, screening, and public health planning. As deployment expands, privacy risk arises from model-mediated leakage, yet its prevalence and severity remain poorly quantified. Models can disclose sensitive training artifacts, enabling patient re-identification in ways not captured by data-handling controls alone. As a result, existing frameworks, including HIPAA and GDPR, offer limited protection against assessing and addressing. We propose a practical framework for assessing privacy risk in clinical foundation models, illustrate realistic leakage scenarios across deployment settings, map them to legal regimes, and outline complementary technical and legal mitigations. Our analysis provides a context-aware risk assessment grounded in realistic usage to preserve the value of medical foundation models while rigorously safeguarding patient privacy.

cs.AI↗

arXiv2026

Lexplorer: Navigating the Complexity of Legal Document Landscapes

As technological and social innovations create novel regulatory challenges, legal systems grow in complexity - increasing the need for interfaces that enable effective interactions with legal document collections. Through interviews with legal scholars (n=15), we find that supporting legal work requires going beyond retrieval-centered legal-information-system paradigms. Hence, we propose Lexplorer, a flexible interface for exploring, navigating, and analyzing legal documents, based on a taxonomy capturing user intents. Distinguishing text and data views for one, few, and many documents, Lexplorer enables context-sensitive interactions with evolving collections of interconnected legal texts, facilitating Adaptive Meaning Construction in law. We evaluate Lexplorer with legal scholars (n=20) in the context of European Union law, validating our elicited requirements, intent taxonomy, and prototype design. Resulting from a close collaboration between visual-analytics researchers and legal scholars, our work also provides nuanced insights into the process required to design interactive systems for expert domains driven by implicit methodological knowledge.

cs.HC↗

arXiv2026

Relational Dissonance in Human-AI Interactions: The Case of Knowledge Work

When AI systems allow human-like communication, they elicit increasingly complex relational responses. Knowledge workers face a particular challenge: They approach these systems as tools while interacting with them in ways that resemble human social interaction. To understand the relational contexts that arise when humans engage with anthropomorphic conversational agents, we need to expand existing human-computer interaction frameworks. Through three workshops with qualitative researchers, we found that the fundamental ontological and relational ambiguities inherent in anthropomorphic conversational agents make it difficult for individuals to maintain consistent relational stances toward them. Our findings indicate that people's articulated positioning toward such agents often differs from the relational dynamics that occur during interactions. We propose the concept of relational dissonance to help researchers, designers, and policymakers recognize the resulting tensions in the development, deployment, and governance of anthropomorphic conversational agents and address the need for relational transparency.

cs.HC↗

arXiv2026

Real Preferences Under Arbitrary Norms

Whether the goal is to analyze voting behavior, locate facilities, or recommend products, the problem of translating between (ordinal) rankings and (numerical) utilities arises naturally in many contexts. This task is commonly approached by representing both the individuals doing the ranking (voters) and the items to be ranked (alternatives) in a shared metric space, where ordinal preferences are translated into relationships between pairwise distances. Prior work has established that any collection of rankings with $n$ voters and $m$ alternatives (preference profile) can be embedded into $d$-dimensional Euclidean space for $d \geq \min\{n,m-1\}$ under the Euclidean norm and the Manhattan norm. We show that this holds for all $p$-norms and establish that any pair of rankings can be embedded into $R^2$ under arbitrary norms, significantly expanding the reach of spatial preference models.

econ.TH↗

arXiv2025

The Power of Network Pluralism: Multi-Perspective Modeling of Heterogeneous Legal Document Networks

Insights are relative - influenced by a range of factors such as assumptions, scopes, or methods that together define a research perspective. In normative and empirical fields alike, this insight has led to the conclusion that no single perspective can generate complete knowledge. As a response, epistemological pluralism mandates that researchers consider multiple perspectives simultaneously to obtain a holistic understanding of their phenomenon under study. Translating this mandate to network science, our work introduces Network Pluralism as a conceptual framework that leverages multi-perspectivity to yield more complete, meaningful, and robust results. We develop and demonstrate the benefits of this approach via a hands-on analysis of complex legal systems, constructing a network space from references across documents from different branches of government as well as including organizational hierarchy above and fine-grained structure below the document level. Leveraging the resulting heterogeneity in a multi-network analysis, we show how complementing perspectives can help contextualize otherwise high-level findings, how contrasting several networks derived from the same data enables researchers to learn by difference, and how relating metrics to perspectives may increase the transparency and robustness of network-analytical results. To analyze a space of networks as perspectives, researchers need to map dimensions of variation in a given domain to network-modeling decisions and network-metric parameters. While this remains a challenging and inherently interdisciplinary task, our work acts as a blueprint to facilitate the broader adoption of Network Pluralism in domain-driven network research.

cs.SI↗

arXiv2025

New Limits on Distributed Quantum Advantage: Dequantizing Linear Programs

In this work, we give two results that put new limits on distributed quantum advantage in the context of the LOCAL model of distributed computing. First, we show that there is no distributed quantum advantage for any linear program. Put otherwise, if there is a quantum-LOCAL algorithm $\mathcal{A}$ that finds an $α$-approximation of some linear optimization problem $Π$ in $T$ communication rounds, we can construct a classical, deterministic LOCAL algorithm $\mathcal{A}'$ that finds an $α$-approximation of $Π$ in $T$ rounds. As a corollary, all classical lower bounds for linear programs, including the KMW bound, hold verbatim in quantum-LOCAL. Second, using the above result, we show that there exists a locally checkable labeling problem (LCL) for which quantum-LOCAL is strictly weaker than the classical deterministic SLOCAL model. Our results extend from quantum-LOCAL also to finitely dependent and non-signaling distributions, and one of the corollaries of our work is that the non-signaling model and the SLOCAL model are incomparable in the context of LCL problems: By prior work, there exists an LCL problem for which SLOCAL is strictly weaker than the non-signaling model, and our work provides a separation in the opposite direction.

cs.DC↗

arXiv2025

Low-dimensional embeddings of high-dimensional data

Large collections of high-dimensional data have become nearly ubiquitous across many academic fields and application domains, ranging from biology to the humanities. Since working directly with high-dimensional data poses challenges, the demand for algorithms that create low-dimensional representations, or embeddings, for data visualization, exploration, and analysis is now greater than ever. In recent years, numerous embedding algorithms have been developed, and their usage has become widespread in research and industry. This surge of interest has resulted in a large and fragmented research field that faces technical challenges alongside fundamental debates, and it has left practitioners without clear guidance on how to effectively employ existing methods. Aiming to increase coherence and facilitate future work, in this review we provide a detailed and critical overview of recent developments, derive a list of best practices for creating and using low-dimensional embeddings, evaluate popular approaches on a variety of datasets, and discuss the remaining challenges and open problems in the field.

cs.LG↗

arXiv2025

No Metric to Rule Them All: Toward Principled Evaluations of Graph-Learning Datasets

Benchmark datasets have proved pivotal to the success of graph learning, and good benchmark datasets are crucial to guide the development of the field. Recent research has highlighted problems with graph-learning datasets and benchmarking practices -- revealing, for example, that methods which ignore the graph structure can outperform graph-based approaches. Such findings raise two questions: (1) What makes a good graph-learning dataset, and (2) how can we evaluate dataset quality in graph learning? Our work addresses these questions. As the classic evaluation setup uses datasets to evaluate models, it does not apply to dataset evaluation. Hence, we start from first principles. Observing that graph-learning datasets uniquely combine two modes -- graph structure and node features --, we introduce Rings, a flexible and extensible mode-perturbation framework to assess the quality of graph-learning datasets based on dataset ablations -- i.e., quantifying differences between the original dataset and its perturbed representations. Within this framework, we propose two measures -- performance separability and mode complementarity -- as evaluation tools, each assessing the capacity of a graph dataset to benchmark the power and efficacy of graph-learning methods from a distinct angle. We demonstrate the utility of our framework for dataset evaluation via extensive experiments on graph-level tasks and derive actionable recommendations for improving the evaluation of graph-learning methods. Our work opens new research directions in data-centric graph learning, and it constitutes a step toward the systematic evaluation of evaluations.

cs.LG↗

arXiv2024

Model-Agnostic Approximation of Constrained Forest Problems

Constrained Forest Problems (CFPs) as introduced by Goemans and Williamson in 1995 capture a wide range of network design problems with edge subsets as solutions, such as Minimum Spanning Tree, Steiner Forest, and Point-to-Point Connection. While individual CFPs have been studied extensively in individual computational models, a unified approach to solving general CFPs in multiple computational models has been lacking. Against this background, we present the shell-decomposition algorithm, a model-agnostic meta-algorithm that efficiently computes a $(2+ε)$-approximation to CFPs for a broad class of forest functions. To demonstrate the power and flexibility of this result, we instantiate our algorithm for 3 fundamental, NP-hard CFPs in 3 different computational models. For example, for constant $ε$, we obtain the following $(2+ε)$-approximations in the Congest model: 1. For Steiner Forest specified via input components, where each node knows the identifier of one of $k$ disjoint subsets of $V$, we achieve a deterministic $(2+ε)$-approximation in $O(\sqrt{n}+D+k)$ rounds, where $D$ is the hop diameter of the graph. 2. For Steiner Forest specified via symmetric connection requests, where connection requests are issued to pairs of nodes, we leverage randomized equality testing to reduce the running time to $O(\sqrt{n}+D)$, succeeding with high probability. 3. For Point-to-Point Connection, we provide a $(2+ε)$-approximation in $O(\sqrt{n}+D)$ rounds. 4. For Facility Placement and Connection, a relative of non-metric Facility Location, we obtain a $(2+ε)$-approximation in $O(\sqrt{n}+D)$ rounds. We further show how to replace the $\sqrt{n}+D$ term by the complexity of solving Partwise Aggregation, achieving (near-)universal optimality in any setting in which a solution to Partwise Aggregation in near-shortcut-quality time is known.

cs.DC↗

arXiv2024

Mapping the Multiverse of Latent Representations

Echoing recent calls to counter reliability and robustness concerns in machine learning via multiverse analysis, we present PRESTO, a principled framework for mapping the multiverse of machine-learning models that rely on latent representations. Although such models enjoy widespread adoption, the variability in their embeddings remains poorly understood, resulting in unnecessary complexity and untrustworthy representations. Our framework uses persistent homology to characterize the latent spaces arising from different combinations of diverse machine-learning methods, (hyper)parameter configurations, and datasets, allowing us to measure their pairwise (dis)similarity and statistically reason about their distributions. As we demonstrate both theoretically and empirically, our pipeline preserves desirable properties of collections of latent representations, and it can be leveraged to perform sensitivity analysis, detect anomalous embeddings, or efficiently and effectively navigate hyperparameter search spaces.

cs.LG↗

arXiv2023

All the World's a (Hyper)Graph: A Data Drama

We introduce Hyperbard, a dataset of diverse relational data representations derived from Shakespeare's plays. Our representations range from simple graphs capturing character co-occurrence in single scenes to hypergraphs encoding complex communication settings and character contributions as hyperedges with edge-specific node weights. By making multiple intuitive representations readily available for experimentation, we facilitate rigorous representation robustness checks in graph learning, graph mining, and network analysis, highlighting the advantages and drawbacks of specific representations. Leveraging the data released in Hyperbard, we demonstrate that many solutions to popular graph mining problems are highly dependent on the representation choice, thus calling current graph curation practices into question. As an homage to our data source, and asserting that science can also be art, we present all our points in the form of a play.

cs.LG↗

arXiv2023

Reducing Exposure to Harmful Content via Graph Rewiring

Most media content consumed today is provided by digital platforms that aggregate input from diverse sources, where access to information is mediated by recommendation algorithms. One principal challenge in this context is dealing with content that is considered harmful. Striking a balance between competing stakeholder interests, rather than block harmful content altogether, one approach is to minimize the exposure to such content that is induced specifically by algorithmic recommendations. Hence, modeling media items and recommendations as a directed graph, we study the problem of reducing the exposure to harmful content via edge rewiring. We formalize this problem using absorbing random walks, and prove that it is NP-hard and NP-hard to approximate to within an additive error, while under realistic assumptions, the greedy method yields a (1-1/e)-approximation. Thus, we introduce Gamine, a fast greedy algorithm that can reduce the exposure to harmful content with or without quality constraints on recommendations. By performing just 100 rewirings on YouTube graphs with several hundred thousand edges, Gamine reduces the initial exposure by 50%, while ensuring that its recommendations are at most 5% less relevant than the original recommendations. Through extensive experiments on synthetic data and real-world data from video recommendation and news feed applications, we confirm the effectiveness, robustness, and efficiency of Gamine in practice.

cs.SI↗

arXiv2023

Evaluating the "Learning on Graphs" Conference Experience

With machine learning conferences growing ever larger, and reviewing processes becoming increasingly elaborate, more data-driven insights into their workings are required. In this report, we present the results of a survey accompanying the first "Learning on Graphs" (LoG) Conference. The survey was directed to evaluate the submission and review process from different perspectives, including authors, reviewers, and area chairs alike.

cs.LG↗

arXiv2023

Ollivier-Ricci Curvature for Hypergraphs: A Unified Framework

Bridging geometry and topology, curvature is a powerful and expressive invariant. While the utility of curvature has been theoretically and empirically confirmed in the context of manifolds and graphs, its generalization to the emerging domain of hypergraphs has remained largely unexplored. On graphs, the Ollivier-Ricci curvature measures differences between random walks via Wasserstein distances, thus grounding a geometric concept in ideas from probability theory and optimal transport. We develop ORCHID, a flexible framework generalizing Ollivier-Ricci curvature to hypergraphs, and prove that the resulting curvatures have favorable theoretical properties. Through extensive experiments on synthetic and real-world hypergraphs from different domains, we demonstrate that ORCHID curvatures are both scalable and useful to perform a variety of hypergraph tasks in practice.

cs.LG↗

arXiv2022

Sharing and Caring: Creating a Culture of Constructive Criticism in Computational Legal Studies

We introduce seven foundational principles for creating a culture of constructive criticism in computational legal studies. Beginning by challenging the current perception of papers as the primary scholarly output, we call for a more comprehensive interpretation of publications. We then suggest to make these publications computationally reproducible, releasing all of the data and all of the code all of the time, on time, and in the most functioning form possible. Subsequently, we invite constructive criticism in all phases of the publication life cycle. We posit that our proposals will help form our field, and float the idea of marking this maturity by the creation of a modern flagship publication outlet for computational legal studies.

cs.CY↗

arXiv2022

Differentially Describing Groups of Graphs

How does neural connectivity in autistic children differ from neural connectivity in healthy children or autistic youths? What patterns in global trade networks are shared across classes of goods, and how do these patterns change over time? Answering questions like these requires us to differentially describe groups of graphs: Given a set of graphs and a partition of these graphs into groups, discover what graphs in one group have in common, how they systematically differ from graphs in other groups, and how multiple groups of graphs are related. We refer to this task as graph group analysis, which seeks to describe similarities and differences between graph groups by means of statistically significant subgraphs. To perform graph group analysis, we introduce Gragra, which uses maximum entropy modeling to identify a non-redundant set of subgraphs with statistically significant associations to one or more graph groups. Through an extensive set of experiments on a wide range of synthetic and real-world graph groups, we confirm that Gragra works well in practice.

cs.SI↗

arXiv2021

Law Smells: Defining and Detecting Problematic Patterns in Legal Drafting

Building on the computer science concept of code smells, we initiate the study of law smells, i.e., patterns in legal texts that pose threats to the comprehensibility and maintainability of the law. With five intuitive law smells as running examples - namely, duplicated phrase, long element, large reference tree, ambiguous syntax, and natural language obsession -, we develop a comprehensive law smell taxonomy. This taxonomy classifies law smells by when they can be detected, which aspects of law they relate to, and how they can be discovered. We introduce text-based and graph-based methods to identify instances of law smells, confirming their utility in practice using the United States Code as a test case. Our work demonstrates how ideas from software engineering can be leveraged to assess and improve the quality of legal code, thus drawing attention to an understudied area in the intersection of law and computer science and highlighting the potential of computational legal drafting.

cs.IR↗

arXiv2021

Simplify Your Law: Using Information Theory to Deduplicate Legal Documents

Textual redundancy is one of the main challenges to ensuring that legal texts remain comprehensible and maintainable. Drawing inspiration from the refactoring literature in software engineering, which has developed methods to expose and eliminate duplicated code, we introduce the duplicated phrase detection problem for legal texts and propose the Dupex algorithm to solve it. Leveraging the Minimum Description Length principle from information theory, Dupex identifies a set of duplicated phrases, called patterns, that together best compress a given input text. Through an extensive set of experiments on the Titles of the United States Code, we confirm that our algorithm works well in practice: Dupex will help you simplify your law.

cs.CL↗