arXiv subjects

Xi He

Publications and source records attributed to Xi He.

At least 37 records · Page 2Linked to original sources

arXiv2025

Differentially Private Data Generation with Missing Data

Despite several works that succeed in generating synthetic data with differential privacy (DP) guarantees, they are inadequate for generating high-quality synthetic data when the input data has missing values. In this work, we formalize the problems of DP synthetic data with missing values and propose three effective adaptive strategies that significantly improve the utility of the synthetic data on four real-world datasets with different types and levels of missing data and privacy requirements. We also identify the relationship between privacy impact for the complete ground truth data and incomplete data for these DP synthetic data generation algorithms. We model the missing mechanisms as a sampling process to obtain tighter upper bounds for the privacy guarantees to the ground truth data. Overall, this study contributes to a better understanding of the challenges and opportunities for using private synthetic data generation algorithms in the presence of missing data.

cs.DB↗

arXiv2025

VDDP: Verifiable Distributed Differential Privacy under the Client-Server-Verifier Setup

Although differential privacy (DP) is widely regarded as the de facto standard for data privacy, its implementation remains vulnerable to unfaithful execution by servers, particularly in distributed settings. In such cases, servers may sample noise from incorrect distributions or generate correlated noise while appearing to follow established protocols. This work addresses these malicious behaviours in a distributed client-server-verifier setup, under Verifiable Distributed Differential Privacy (VDDP), a novel framework for the verifiable execution of distributed DP mechanisms. We systematically capture end-to-end security and privacy guarantees against potentially colluding adversarial behaviours of clients, servers, and verifiers by characterizing the connections and distinctions between VDDP and zero-knowledge proofs (ZKPs). We develop three novel and efficient instantiations of VDDP: (1) the Verifiable Distributed Discrete Laplace Mechanism (VDDLM), which achieves up to a 400,000x improvement in proof generation efficiency with only 0.1--0.2x error compared with the previous state-of-the-art verifiable differentially private mechanism and includes a tight privacy analysis that accounts for all additional privacy losses due to numerical imprecisions, applicable to other secure computation protocols for DP mechanisms based on cryptography; (2) the Verifiable Distributed Discrete Gaussian Mechanism (VDDGM), an extension of VDDLM that incurs limited overhead in real-world applications; and (3) an improved solution to Verifiable Randomized Response (VRR) under local DP, as a special case of VDDP, achieving up to a 5,000x reduction in communication costs and verifier overhead.

cs.CR↗

arXiv2025

Paper2Poster: Towards Multimodal Poster Automation from Scientific Papers

Academic poster generation is a crucial yet challenging task in scientific communication, requiring the compression of long-context interleaved documents into a single, visually coherent page. To address this challenge, we introduce the first benchmark and metric suite for poster generation, which pairs recent conference papers with author-designed posters and evaluates outputs on (i)Visual Quality-semantic alignment with human posters, (ii)Textual Coherence-language fluency, (iii)Holistic Assessment-six fine-grained aesthetic and informational criteria scored by a VLM-as-judge, and notably (iv)PaperQuiz-the poster's ability to convey core paper content as measured by VLMs answering generated quizzes. Building on this benchmark, we propose PosterAgent, a top-down, visual-in-the-loop multi-agent pipeline: the (a)Parser distills the paper into a structured asset library; the (b)Planner aligns text-visual pairs into a binary-tree layout that preserves reading order and spatial balance; and the (c)Painter-Commenter loop refines each panel by executing rendering code and using VLM feedback to eliminate overflow and ensure alignment. In our comprehensive evaluation, we find that GPT-4o outputs-though visually appealing at first glance-often exhibit noisy text and poor PaperQuiz scores, and we find that reader engagement is the primary aesthetic bottleneck, as human-designed posters rely largely on visual semantics to convey meaning. Our fully open-source variants (e.g. based on the Qwen-2.5 series) outperform existing 4o-driven multi-agent systems across nearly all metrics, while using 87% fewer tokens. It transforms a 22-page paper into a finalized yet editable .pptx poster - all for just $0.005. These findings chart clear directions for the next generation of fully automated poster-generation models. The code and datasets are available at https://github.com/Paper2Poster/Paper2Poster.

cs.CV↗

arXiv2025

Foundational theory for optimal decision tree problems. I. Algorithmic and geometric foundations

In the first paper (part I) of this series of two, we introduce four novel definitions of the ODT problems: three for size-constrained trees and one for depth-constrained trees. These definitions are stated unambiguously through executable recursive programs, satisfying all criteria we propose for a formal specification. In this sense, they resemble the "standard form" used in the study of general-purpose solvers. Grounded in algebraic programming theory-a relational formalism for deriving correct-by-construction algorithms from specifications-we can not only establish the existence or nonexistence of dynamic programming solutions but also derive them constructively whenever they exist. Consequently, the four generic problem definitions yield four novel optimal algorithms for ODT problems with arbitrary splitting rules that satisfy the axioms and objective functions of a given form. These algorithms encompass the known depth-constrained, axis-parallel ODT algorithm as the special case, while providing a unified, efficient, and elegant solution for the general ODT problem. In Part II, we present the first optimal hypersurface decision tree algorithm and provide comprehensive experiments against axis-parallel decision tree algorithms, including heuristic CART and state-of-the-art optimal methods. The results demonstrate the significant potential of decision trees with flexible splitting rules. Moreover, our framework is readily extendable to support algorithms for constructing even more flexible decision trees, including those with mixed splitting rules.

cs.LG↗

arXiv2025

Proper decision trees: An axiomatic framework for solving optimal decision tree problems with arbitrary splitting rules

We present an axiomatic framework for analyzing the algorithmic properties of decision trees. This framework supports the classification of decision tree problems through structural and ancestral constraints within a rigorous mathematical foundation. The central focus of this paper is a special class of decision tree problems-which we term proper decision trees-due to their versatility and effectiveness. In terms of versatility, this class subsumes several well-known data structures, including binary space partitioning trees, K-D trees, and machine learning decision tree models. Regarding effectiveness, we prove that only proper decision trees can be uniquely characterized as K-permutations, whereas typical non-proper decision trees correspond to binary-labeled decision trees with substantially greater complexity. Using this formal characterization, we develop a generic algorithmic approach for solving optimal decision tree problems over arbitrary splitting rules and objective functions for proper decision trees. We constructively derive a generic dynamic programming recursion for solving these problems exactly. However, we show that memoization is generally impractical in terms of space complexity, as both datasets and subtrees must be stored. This result contradicts claims in the literature that suggest a trade-off between memoizing datasets and subtrees. Our framework further accommodates constraints such as tree depth and leaf size, and can be accelerated using techniques such as thinning. Finally, we extend our analysis to several non-proper decision trees, including the commonly studied decision tree over binary feature data, the binary search tree, and the tree structure arising in the matrix chain multiplication problem. We demonstrate how these problems can be solved by appropriately modifying or discarding certain axioms.

cs.LG↗

arXiv2025

MaskSQL: Safeguarding Privacy for LLM-Based Text-to-SQL via Abstraction

Large language models (LLMs) have shown promising performance on tasks that require reasoning, such as text-to-SQL, code generation, and debugging. However, regulatory frameworks with strict privacy requirements constrain their integration into sensitive systems. State-of-the-art LLMs are also proprietary, costly, and resource-intensive, making local deployment impractical. Consequently, utilizing such LLMs often requires sharing data with third-party providers, raising privacy concerns and risking noncompliance with regulations. Although fine-tuned small language models (SLMs) can outperform LLMs on certain tasks and be deployed locally to mitigate privacy concerns, they underperform on more complex tasks such as text-to-SQL translation. In this work, we introduce MaskSQL, a text-to-SQL framework that utilizes abstraction as a privacy protection mechanism to mask sensitive information in LLM prompts. Unlike redaction, which removes content entirely, or generalization, which broadens tokens, abstraction retains essential information while discarding unnecessary details, striking an effective privacy-utility balance for the text-to-SQL task. Moreover, by providing mechanisms to control the privacy-utility tradeoff, MaskSQL facilitates adoption across a broader range of use cases. Our experimental results show that MaskSQL outperforms leading SLM-based text-to-SQL models and achieves performance approaching state-of-the-art LLM-based models, while preserving privacy.

cs.CR↗

arXiv2025

Computing Inconsistency Measures Under Differential Privacy

Assessing data quality is crucial to knowing whether and how to use the data for different purposes. Specifically, given a collection of integrity constraints, various ways have been proposed to quantify the inconsistency of a database. Inconsistency measures are particularly important when we wish to assess the quality of private data without revealing sensitive information. We study the estimation of inconsistency measures for a database protected under Differential Privacy (DP). Such estimation is nontrivial since some measures intrinsically query sensitive information, and the computation of others involves functions on underlying sensitive data. Among five inconsistency measures that have been proposed in recent work, we identify that two are intractable in the DP setting. The major challenge for the other three is high sensitivity: adding or removing one tuple from the dataset may significantly affect the outcome. To mitigate that, we model the dataset using a conflict graph and investigate private graph statistics to estimate these measures. The proposed machinery includes adapting graph-projection techniques with parameter selection optimizations on the conflict graph and a DP variant of approximate vertex cover size. We experimentally show that we can effectively compute DP estimates of the three measures on five real-world datasets with denial constraints, where the density of the conflict graphs highly varies.

cs.DB↗

arXiv2025

Collapsing domain walls with $\mathbb{Z}_2$-violating coupling to thermalized fermions and their impact on gravitational wave detections

We study the dynamics of domain walls formed through the spontaneous breaking of an approximate $\mathbb{Z}_2$ symmetry in a scalar field, focusing on their collapse under the influence of quantum and thermal corrections induced by a $\mathbb{Z}_2$-violating Yukawa coupling to Dirac fermions in the thermal bath. The thermal effects make the potential bias between the true and false vacua dependent on the temperature and may lead to notable variations in the annihilation temperature of domain walls, in addition to the shift caused by temperature-independent quantum corrections. These modifications could substantially alter the gravitational wave spectrum produced by collapsing domain walls, potentially providing observable signatures for future gravitational wave detection experiments.

hep-ph↗

arXiv2025

Adopt a PET! An Exploration of PETs, Policy, and Practicalities for Industry in Canada

Privacy is an instance of a social norm formed through legal, technical, and cultural dimensions. Institutions such as regulators, industry, and researchers act as societal agents that both influence and respond to evolving norms. Attempts to promote privacy are often ineffective unless they account for this complexity and the dynamic interactions among these actors. Privacy enhancing technologies (PETs) are technical solutions for privacy issues that enable collaborative data analysis, allowing for the development of solutions that benefit society, all while ensuring the privacy of individuals whose data is being used. However, despite increased privacy challenges and a corresponding increase in new regulations being proposed by governments across the globe, a low adoption rate of PETs persists. In this work, we investigate the factors influencing industry's decision-making processes around PETs adoption as well as the extent to which privacy regulations inspire such adoption. We conducted a qualitative survey study with 22 industry participants from across Canada to investigate how businesses in Canada make decisions to adopt novel technologies and how new privacy regulations impact their business processes. Informed by the results of our analysis, we make recommendations for industry, researchers, and policymakers on how to support what each of them seeks from the other when attempting to improve digital privacy protections. By advancing our understanding of what challenges the industry faces, we increase the effectiveness of future privacy research that aims to help overcome these issues.

cs.CR↗

arXiv2025

Cybroc: Cyborgizing Broccoli for Longevity

Cybroc is a series of kinetic art installations exploring the recent proliferating populist longevity activism through the satirical cyborgization of broccoli. The artwork augments the symbol of health food-broccoli-with prosthetic limbs to perform so-called longevity-enhancing exercises such as cold plunges, treadmill running, brachiation (arm-swinging), sled pushing, etc.-all simulations of primal human survival tasks reframed as modern fitness routines. Despite its mechanical augmentations, the broccoli's inevitable decay and rotting after exhibiting high-intensity performances prompts reflection on the limits of biological enhancement and the ethics of human enhancement beyond natural capabilities, particularly transhumanist ideals. By juxtaposing a symbolic healthy vegetable with cutting-edge concepts of human enhancement, Cybroc challenges viewers to consider the intersection of nature, technology, and the human quest for extended lifespan in our transhuman era.

cs.CY↗

arXiv2025

Survival Analysis with Graph-Based Regularization for Predictors

We study the variable selection problem in survival analysis to identify the most important factors affecting survival time. Our method incorporates prior knowledge of mutual correlations among variables, represented through a graph. We utilize the Cox proportional hazard model with a graph-based regularizer for variable selection. We present a computationally efficient algorithm developed to solve the graph regularized maximum likelihood problem by establishing connections with the group lasso, and provide theoretical guarantees about the recovery error and asymptotic distribution of the proposed estimators. The improved performance of the proposed approach compared with existing methods are demonstrated in both synthetic and real organ transplantation datasets.

math.ST↗

arXiv2024

Data Poisoning Attacks to Local Differential Privacy Protocols for Graphs

Graph analysis has become increasingly popular with the prevalence of big data and machine learning. Traditional graph data analysis methods often assume the existence of a trusted third party to collect and store the graph data, which does not align with real-world situations. To address this, some research has proposed utilizing Local Differential Privacy (LDP) to collect graph data or graph metrics (e.g., clustering coefficient). This line of research focuses on collecting two atomic graph metrics (the adjacency bit vectors and node degrees) from each node locally under LDP to synthesize an entire graph or generate graph metrics. However, they have not considered the security issues of LDP for graphs. In this paper, we bridge the gap by demonstrating that an attacker can inject fake users into LDP protocols for graphs and design data poisoning attacks to degrade the quality of graph metrics. In particular, we present three data poisoning attacks to LDP protocols for graphs. As a proof of concept, we focus on data poisoning attacks on two classical graph metrics: degree centrality and clustering coefficient. We further design two countermeasures for these data poisoning attacks. Experimental study on real-world datasets demonstrates that our attacks can largely degrade the quality of collected graph metrics, and the proposed countermeasures cannot effectively offset the effect, which calls for the development of new defenses.

cs.CR↗

arXiv2024

ClavaDDPM: Multi-relational Data Synthesis with Cluster-guided Diffusion Models

Recent research in tabular data synthesis has focused on single tables, whereas real-world applications often involve complex data with tens or hundreds of interconnected tables. Previous approaches to synthesizing multi-relational (multi-table) data fall short in two key aspects: scalability for larger datasets and capturing long-range dependencies, such as correlations between attributes spread across different tables. Inspired by the success of diffusion models in tabular data modeling, we introduce $\textbf{C}luster$ $\textbf{La}tent$ $\textbf{Va}riable$ $guided$ $\textbf{D}enoising$ $\textbf{D}iffusion$ $\textbf{P}robabilistic$ $\textbf{M}odels$ (ClavaDDPM). This novel approach leverages clustering labels as intermediaries to model relationships between tables, specifically focusing on foreign key constraints. ClavaDDPM leverages the robust generation capabilities of diffusion models while incorporating efficient algorithms to propagate the learned latent variables across tables. This enables ClavaDDPM to capture long-range dependencies effectively. Extensive evaluations on multi-table datasets of varying sizes show that ClavaDDPM significantly outperforms existing methods for these long-range dependencies while remaining competitive on utility metrics for single-table data.

cs.AI↗

arXiv2024

Distribution alignment based transfer fusion frameworks on quantum devices for seeking quantum advantages

The scarcity of labelled data is specifically an urgent challenge in the field of quantum machine learning (QML). Two transfer fusion frameworks are proposed in this paper to predict the labels of a target domain data by aligning its distribution to a different but related labelled source domain on quantum devices. The frameworks fuses the quantum data from two different, but related domains through a quantum information infusion channel. The predicting tasks in the target domain can be achieved with quantum advantages by post-processing quantum measurement results. One framework, the quantum basic linear algebra subroutines (QBLAS) based implementation, can theoretically achieve the procedure of transfer fusion with quadratic speedup on a universal quantum computer. In addition, the other framework, a hardware-scalable architecture, is implemented on the noisy intermediate-scale quantum (NISQ) devices through a variational hybrid quantum-classical procedure. Numerical experiments on the synthetic and handwritten digits datasets demonstrate that the variatioinal transfer fusion (TF) framework can reach state-of-the-art (SOTA) quantum DA method performance.

cs.CV↗

arXiv2024

ProBE: Proportioning Privacy Budget for Complex Exploratory Decision Support

This paper studies privacy in the context of complex decision support queries composed of multiple conditions on different aggregate statistics combined using disjunction and conjunction operators. Utility requirements for such queries necessitate the need for private mechanisms that guarantee a bound on the false negative and false positive errors. This paper formally defines complex decision support queries and their accuracy requirements, and provides algorithms that proportion the existing budget to optimally minimize privacy loss while supporting a bounded guarantee on the accuracy. Our experimental results on multiple real-life datasets show that our algorithms successfully maintain such utility guarantees, while also minimizing privacy loss.

cs.DB↗

arXiv2024

EKM: An exact, polynomial-time algorithm for the $K$-medoids problem

The $K$-medoids problem is a challenging combinatorial clustering task, widely used in data analysis applications. While numerous algorithms have been proposed to solve this problem, none of these are able to obtain an exact (globally optimal) solution for the problem in polynomial time. In this paper, we present EKM: a novel algorithm for solving this problem exactly with worst-case $O\left(N^{K+1}\right)$ time complexity. EKM is developed according to recent advances in transformational programming and combinatorial generation, using formal program derivation steps. The derived algorithm is provably correct by construction. We demonstrate the effectiveness of our algorithm by comparing it against various approximate methods on numerous real-world datasets. We show that the wall-clock run time of our algorithm matches the worst-case time complexity analysis on synthetic datasets, clearly outperforming the exponential time complexity of benchmark branch-and-bound based MIP solvers. To our knowledge, this is the first, rigorously-proven polynomial time, practical algorithm for this ubiquitous problem.

cs.LG↗

arXiv2024

Unbiased Statistical Estimation and Valid Confidence Intervals Under Differential Privacy

We present a method for producing unbiased parameter estimates and valid confidence intervals under the constraints of differential privacy, a formal framework for limiting individual information leakage from sensitive data. Prior work in this area is limited in that it is tailored to calculating confidence intervals for specific statistical procedures, such as mean estimation or simple linear regression. While other recent work can produce confidence intervals for more general sets of procedures, they either yield only approximately unbiased estimates, are designed for one-dimensional outputs, or assume significant user knowledge about the data-generating distribution. Our method induces distributions of mean and covariance estimates via the bag of little bootstraps (BLB) and uses them to privately estimate the parameters' sampling distribution via a generalized version of the CoinPress estimation algorithm. If the user can bound the parameters of the BLB-induced parameters and provide heavier-tailed families, the algorithm produces unbiased parameter estimates and valid confidence intervals which hold with arbitrarily high probability. These results hold in high dimensions and for any estimation procedure which behaves nicely under the bootstrap.

stat.ME↗

arXiv2024

Dynamic programming by polymorphic semiring algebraic shortcut fusion

Dynamic programming (DP) is an algorithmic design paradigm for the efficient, exact solution of otherwise intractable, combinatorial problems. However, DP algorithm design is often presented in an ad-hoc manner. It is sometimes difficult to justify algorithm correctness. To address this issue, this paper presents a rigorous algebraic formalism for systematically deriving DP algorithms, based on semiring polymorphism. We start with a specification, construct an algorithm to compute the required solution which is self-evidently correct because it exhaustively generates and evaluates all possible solutions meeting the specification. We then derive, through the use of shortcut fusion, an implementation of this algorithm which is both efficient and correct. We also demonstrate how, with the use of semiring lifting, the specification can be augmented with combinatorial constraints, showing how these constraints can be fused with the algorithm. We furthermore demonstrate how existing DP algorithms for a given combinatorial problem can be abstracted from their original context and re-purposed. This approach can be applied to the full scope of combinatorial problems expressible in terms of semirings. This includes, for example: optimal probability and Viterbi decoding, probabilistic marginalization, logical inference, fuzzy sets, differentiable softmax, relational and provenance queries. The approach, building on ideas from the existing literature on constructive algorithmics, exploits generic properties of polymorphic functions, tupling and formal sums and algebraic simplifications arising from constraint algebras. We demonstrate the effectiveness of this formalism for some example applications arising in signal processing, bioinformatics and reliability engineering. Python software implementing these algorithms can be downloaded from: http://www.maxlittle.net/software/dppolyalg.zip.

cs.DS↗