arXiv subjects

Makoto Onizuka

Publications and source records attributed to Makoto Onizuka.

At least 19 recordsLinked to original sources

arXiv2026

SilentWood: Efficient Private Inference Over Gradient-Boosting Decision Forests

Gradient boosting decision forests, used by XGBoost or AdaBoost, offer higher accuracy and lower training times than decision trees on large datasets. Private inference protocols for decision trees can preserve both input and tree privacy. However, naively extending them to decision forests by replication leads to impractical running times. In this paper, we propose an efficient private decision inference protocol using homomorphic encryption. We present several optimizations that identify and remove (approximate) duplication between trees, significantly reducing communication and computation costs over the naive approach. We present the private inference protocol for highly scalable gradient boosting decision forests. Our protocol SilentWood is faster than parallel RCC-PDTE by up to 42.5x, Zama's Concrete ML XGBoost by up to 27.8x, and SoK-GGG's two-party garbled circuit protocol by 2.94x.

cs.CR↗

arXiv2026

ShapleyLaw: A Game-Theoretic Approach to Multilingual Scaling Laws

In multilingual pretraining, the test loss of a pretrained model is heavily influenced by the proportion of each language in the pretraining data, namely the \textit{language mixture ratios}. Multilingual scaling laws can predict the test loss under different language mixture ratios and can therefore be used to estimate the optimal ratios. However, the current approaches to multilingual scaling laws do not measure the \textit{cross-lingual transfer} effect, resulting in suboptimal mixture ratios. In this paper, we consider multilingual pretraining as a cooperative game in which each language acts as a player that jointly contributes to pretraining, gaining the resulting reduction in test loss as the payoff. Consequently, from the perspective of cooperative game theory, we quantify the cross-lingual transfer from each language by its contribution in the game, and propose a game-theoretic multilingual scaling law called \textit{ShapleyLaw}. Our experiments show that ShapleyLaw outperforms baseline methods in model performance prediction and language mixture optimization.

cs.CL↗

arXiv2026

LLM-Based Social Simulations Require a Boundary

This position paper argues that LLM-based social simulations require clear boundaries to make meaningful contributions to social science. While Large Language Models (LLMs) offer promising capabilities for simulating human behavior, their tendency to produce homogeneous outputs, acting as an "average persona", fundamentally limits their ability to capture the behavioral diversity essential for complex social dynamics. We examine why heterogeneity matters for social simulations and how current LLMs fall short, analyzing the relationship between mean alignment and variance in LLM-generated behaviors. Through a systematic review of representative studies, we find that validation practices often fail to match the heterogeneity requirements of research questions: while most papers include ground truth comparisons, fewer than half explicitly assess behavioral variance, and most that do report lower variance than human populations. We propose that researchers should: (1) match validation depth to the heterogeneity demands of their research questions, (2) explicitly report variance alongside mean alignment, and (3) constrain claims to collective-level qualitative patterns when variance is insufficient. Rather than dismissing LLM-based simulation, we advocate for a boundary-aware approach that ensures these methods contribute genuine insights to social science.

cs.CY↗

arXiv2026

Seven Security Challenges in Cross-domain Multi-agent LLM Systems

Large language models (LLMs) are rapidly evolving into autonomous agents that cooperate across organizational boundaries, enabling joint disaster response, supply-chain optimization, and other tasks that demand decentralized expertise without surrendering data ownership. Yet, cross-domain collaboration shatters the unified trust assumptions behind current alignment and containment techniques. An agent benign in isolation may, when receiving messages from an untrusted peer, leak secrets or violate policy, producing risks driven by emergent multi-agent dynamics rather than classical software bugs. This position paper maps the security agenda for cross-domain multi-agent LLM systems. We introduce seven categories of novel security challenges, for each of which we also present plausible attacks, security evaluation metrics, and future research guidelines.

cs.CR↗

arXiv2026

Nonlinearity-Aware LoRA: Structured Gate Adaptation under Low-Rank Constraints

Low-rank adaptation (LoRA) is commonly viewed as an update-space approximation to full fine-tuning, yet this view is incomplete for self-gated Transformer feed-forward networks. In gated FFNs, a low-rank residual can change not only projected features but also the nonlinear selection weights that determine which channels contribute to the output. We formalize this effect as selection misalignment and connect it to the local effective homogeneity of self-gated activations. This motivates a nonlinearity-aware principle for parameter-efficient fine-tuning: low-rank updates should allocate capacity to gate channels whose nonlinear states remain responsive and should shape the temporal evolution of selection. We propose NA-LoRA, a training-only method with two lightweight mechanisms: a derivative-based temporal-importance mask for gate-related LoRA updates and an activation-specific step-scaling rule when a meaningful coarse effective-homogeneity partition is available. NA-LoRA adds no auxiliary loss and incurs no inference-time overhead. Experiments on language-model fine-tuning and vision-language transfer benchmarks show that NA-LoRA consistently improves over vanilla LoRA and is competitive with or better than strong PEFT variants.

cs.LG↗

arXiv2026

Graph Neural Network leveraging Higher-order Class Label Connectivity for Heterophilous Graphs

Node classification in graph neural networks (GNNs) has been widely applied in various fields of graph analysis. GNNs achieve high-accuracy node classification in homophilous graphs, where nodes with the same class label tend to be connected. However, their performance remains limited in heterophilous graphs, where nodes with different class labels are more likely to be connected. In particular, current GNNs derived from graph convolutional networks cannot capture higher-order class label connectivity, which is frequently observed in real-world heterophilous graphs. To address this issue, we propose a novel classifier, Label Context Classifier (LCC), designed to capture higher-order class label connectivity in directed graphs. LCC estimates the class label of a target node by leveraging label context embeddings that are generated through four distinct types of walks. In addition, our approach allows the integration of LCC and any GNN by adaptively learning their importance. Experimental results demonstrate that GNNs integrated with LCC outperform SOTA methods and the label context embeddings improve the node classification performance in heterophilous directed graphs.

cs.LG↗

arXiv2026

Workload acceleration by optimizing materialized view selection using local search

The growing size of database workloads has made view selection a key performance challenge. Materializing frequent sub-queries in workloads improves query efficiency, but it incurs significant view maintenance costs due to updates. Although existing methods such as BIGSUBS address this trade-off between the benefit of using materialized views and the overhead of view maintenance, they have two drawbacks: insufficient maintenance cost modeling and ineffective view selection due to probabilistic techniques. We propose a novel view selection method that incorporates incremental view maintenance cost directly into the optimization objective of an integer linear program and applies local search to efficiently explore the solution space. In order to apply local search to the view selection problem, we develop neighboring solutions using sub-query containment, and select initial solutions based on sub-query frequency, utility, or utility per storage unit. Experiments using Redbench, a benchmark simulating real-world query workloads on Amazon Redshift, show that our approach outperforms BIGSUBS in both optimization utility and the quality of selected views.

cs.DB↗

arXiv2026

Adaptive Layer Selection for Layer-Wise Token Pruning in LLM Inference

Due to the prevalence of large language models (LLMs), key-value (KV) cache reduction for LLM inference has received remarkable attention. Among numerous works that have been proposed in recent years, layer-wise token pruning approaches, which select a subset of tokens at particular layers to retain in KV cache and prune others, are one of the most popular schemes. They primarily adopt a set of pre-defined layers, at which tokens are selected. Such design is inflexible in the sense that the accuracy significantly varies across tasks and deteriorates in harder tasks such as KV retrieval. In this paper, we propose ASL, a training-free method that adaptively chooses the selection layer for KV cache reduction, exploiting the variance of token ranks ordered by attention score. The proposed method balances the performance across different tasks while meeting the user-specified KV budget requirement. ASL operates during the prefilling stage and can be jointly used with existing KV cache reduction methods such as SnapKV to optimize the decoding stage. By evaluations on the InfiniteBench, RULER, and NIAH benchmarks, we show that ASL, equipped with one-shot token selection, adaptively trades inference speed for accuracy, outperforming state-of-the-art layer-wise token pruning methods in difficult tasks.

cs.CL↗

arXiv2025

Legal Fact Prediction: The Missing Piece in Legal Judgment Prediction

Legal judgment prediction (LJP), which enables litigants and their lawyers to forecast judgment outcomes and refine litigation strategies, has emerged as a crucial legal NLP task. Existing studies typically utilize legal facts, i.e., facts that have been established by evidence and determined by the judge, to predict the judgment. However, legal facts are often difficult to obtain in the early stages of litigation, significantly limiting the practical applicability of fact-based LJP. To address this limitation, we propose a novel legal NLP task: legal fact prediction (LFP), which takes the evidence submitted by litigants for trial as input to predict legal facts, thereby empowering fact-based LJP technologies to make predictions in the absence of ground-truth legal facts. We also propose the first benchmark dataset, LFPBench, for evaluating the LFP task. Our extensive experiments on LFPBench demonstrate the effectiveness of LFP-empowered LJP and highlight promising research directions for LFP.

cs.CL↗

arXiv2025

GraphCompliance: Aligning Policy and Context Graphs for LLM-Based Regulatory Compliance

Compliance at web scale poses practical challenges: each request may require a regulatory assessment. Regulatory texts (e.g., the General Data Protection Regulation, GDPR) are cross-referential and normative, while runtime contexts are expressed in unstructured natural language. This setting motivates us to align semantic information in unstructured text with the structured, normative elements of regulations. To this end, we introduce GraphCompliance, a framework that represents regulatory texts as a Policy Graph and runtime contexts as a Context Graph, and aligns them. In this formulation, the policy graph encodes normative structure and cross-references, whereas the context graph formalizes events as subject-action-object (SAO) and entity-relation triples. This alignment anchors the reasoning of a judge large language model (LLM) in structured information and helps reduce the burden of regulatory interpretation and event parsing, enabling a focus on the core reasoning step. In experiments on 300 GDPR-derived real-world scenarios spanning five evaluation tasks, GraphCompliance yields 4.1-7.2 percentage points (pp) higher micro-F1 than LLM-only and RAG baselines, with fewer under- and over-predictions, resulting in higher recall and lower false positive rates. Ablation studies indicate contributions from each graph component, suggesting that structured representations and a judge LLM are complementary for normative reasoning.

cs.AI↗

arXiv2025

Data Overvaluation Attack and Truthful Data Valuation in Federated Learning

In collaborative machine learning (CML), data valuation, i.e., evaluating the contribution of each client's data to the machine learning model, has become a critical task for incentivizing and selecting positive data contributions. However, existing studies often assume that clients engage in data valuation truthfully, overlooking the practical motivation for clients to exaggerate their contributions. To unlock this threat, this paper introduces the data overvaluation attack, enabling strategic clients to have their data significantly overvalued in federated learning, a widely adopted paradigm for decentralized CML. Furthermore, we propose a Bayesian truthful data valuation metric, named Truth-Shapley. Truth-Shapley is the unique metric that guarantees some promising axioms for data valuation while ensuring that clients' optimal strategy is to perform truthful data valuation under certain conditions. Our experiments demonstrate the vulnerability of existing data valuation metrics to the proposed attack and validate the robustness and effectiveness of Truth-Shapley.

cs.CR↗

arXiv2025

Privacy-Enhanced Database Synthesis for Benchmark Publishing (Technical Report)

Benchmarking is crucial for evaluating a DBMS, yet existing benchmarks often fail to reflect the varied nature of user workloads. As a result, there is increasing momentum toward creating databases that incorporate real-world user data to more accurately mirror business environments. However, privacy concerns deter users from directly sharing their data, underscoring the importance of creating synthesized databases for benchmarking that also prioritize privacy protection. Differential privacy (DP)-based data synthesis has become a key method for safeguarding privacy when sharing data, but the focus has largely been on minimizing errors in aggregate queries or downstream ML tasks, with less attention given to benchmarking factors like query runtime performance. This paper delves into differentially private database synthesis specifically for benchmark publishing scenarios, aiming to produce a synthetic database whose benchmarking factors closely resemble those of the original data. Introducing \textit{PrivBench}, an innovative synthesis framework based on sum-product networks (SPNs), we support the synthesis of high-quality benchmark databases that maintain fidelity in both data distribution and query runtime performance while preserving privacy. We validate that PrivBench can ensure database-level DP even when generating multi-relation databases with complex reference relationships. Our extensive experiments show that PrivBench efficiently synthesizes data that maintains privacy and excels in both data distribution similarity and query runtime similarity.

cs.DB↗

arXiv2025

CKGAN: Training Generative Adversarial Networks Using Characteristic Kernel Integral Probability Metrics

In this paper, we propose CKGAN, a novel generative adversarial network (GAN) variant based on an integral probability metrics framework with characteristic kernel (CKIPM). CKIPM, as a distance between two probability distributions, is designed to optimize the lowerbound of the maximum mean discrepancy (MMD) in a reproducing kernel Hilbert space, and thus can be used to train GANs. CKGAN mitigates the notorious problem of mode collapse by mapping the generated images back to random noise. To save the effort of selecting the kernel function manually, we propose a soft selection method to automatically learn a characteristic kernel function. The experimental evaluation conducted on a set of synthetic and real image benchmarks (MNIST, CelebA, etc.) demonstrates that CKGAN generally outperforms other MMD-based GANs. The results also show that at the cost of moderately more training time, the automatically selected kernel function delivers very close performance to the best of manually fine-tuned one on real image benchmarks and is able to improve the performances of other MMD-based GANs.

cs.LG↗

arXiv2025

Ultraverse: A System-Centric Framework for Efficient What-If Analysis for Database-Intensive Web Applications

Existing what-if analysis systems are predominantly tailored to operate on either only the application layer or only the database layer of software. This isolated approach limits their effectiveness in scenarios where intensive interaction between applications and database systems occurs. To address this gap, we introduce Ultraverse, a what-if analysis framework that seamlessly integrates both application and database layers. Ultraverse employs dynamic symbolic execution to effectively translate application code into compact SQL procedure representations, thereby synchronizing application semantics at both SQL and application levels during what-if replays. A novel aspect of Ultraverse is its use of advanced query dependency analysis, which serves two key purposes: (1) it eliminates the need to replay irrelevant transactions that do not influence the outcome, and (2) it facilitates parallel replay of mutually independent transactions, significantly enhancing the analysis efficiency. Ultraverse is applicable to existing unmodified database systems and legacy application codes. Our extensive evaluations of the framework have demonstrated remarkable improvements in what-if analysis speed, achieving performance gains ranging from 7.7x to 291x across diverse benchmarks.

cs.DB↗

arXiv2024

Shall We Team Up: Exploring Spontaneous Cooperation of Competing LLM Agents

Large Language Models (LLMs) have increasingly been utilized in social simulations, where they are often guided by carefully crafted instructions to stably exhibit human-like behaviors during simulations. Nevertheless, we doubt the necessity of shaping agents' behaviors for accurate social simulations. Instead, this paper emphasizes the importance of spontaneous phenomena, wherein agents deeply engage in contexts and make adaptive decisions without explicit directions. We explored spontaneous cooperation across three competitive scenarios and successfully simulated the gradual emergence of cooperation, findings that align closely with human behavioral data. This approach not only aids the computational social science community in bridging the gap between simulations and real-world dynamics but also offers the AI community a novel method to assess LLMs' capability of deliberate reasoning.

cs.AI↗

arXiv2024

Large Language Models as Urban Residents: An LLM Agent Framework for Personal Mobility Generation

This paper introduces a novel approach using Large Language Models (LLMs) integrated into an agent framework for flexible and effective personal mobility generation. LLMs overcome the limitations of previous models by effectively processing semantic data and offering versatility in modeling various tasks. Our approach addresses three research questions: aligning LLMs with real-world urban mobility data, developing reliable activity generation strategies, and exploring LLM applications in urban mobility. The key technical contribution is a novel LLM agent framework that accounts for individual activity patterns and motivations, including a self-consistency approach to align LLMs with real-world activity data and a retrieval-augmented strategy for interpretable activity generation. We evaluate our LLM agent framework and compare it with state-of-the-art personal mobility generation approaches, demonstrating the effectiveness of our approach and its potential applications in urban mobility. Overall, this study marks the pioneering work of designing an LLM agent framework for activity generation based on real-world human activity data, offering a promising tool for urban mobility analysis.

cs.AI↗

arXiv2024

Automatic String Data Validation with Pattern Discovery

In enterprise data pipelines, data insertions occur periodically and may impact downstream services if data quality issues are not addressed. Typically, such problems can be investigated and fixed by on-call engineers, but locating the cause of such problems and fixing errors are often time-consuming. Therefore, automatic data validation is a better solution to defend the system and downstream services by enabling early detection of errors and providing detailed error messages for quick resolution. This paper proposes a self-validate data management system with automatic pattern discovery techniques to verify the correctness of semi-structural string data in enterprise data pipelines. Our solution extracts patterns from historical data and detects erroneous incoming data in a top-down fashion. High-level information of historical data is analyzed to discover the format skeleton of correct values. Fine-grained semantic patterns are then extracted to strike a balance between generalization and specification of the discovered pattern, thus covering as many correct values as possible while avoiding over-fitting. To tackle cold start and rapid data growth, we propose an incremental update strategy and example generalization strategy. Experiments on large-scale industrial and public datasets demonstrate the effectiveness and efficiency of our method compared to alternative solutions. Furthermore, a case study on an industrial platform (Ant Group Inc.) with thousands of applications shows that our system captures meaningful data patterns in daily operations and helps engineers quickly identify errors.

cs.DB↗

arXiv2023

A Simple and Scalable Graph Neural Network for Large Directed Graphs

Node classification is one of the hottest tasks in graph analysis. Though existing studies have explored various node representations in directed and undirected graphs, they have overlooked the distinctions of their capabilities to capture the information of graphs. To tackle the limitation, we investigate various combinations of node representations (aggregated features vs. adjacency lists) and edge direction awareness within an input graph (directed vs. undirected). We address the first empirical study to benchmark the performance of various GNNs that use either combination of node representations and edge direction awareness. Our experiments demonstrate that no single combination stably achieves state-of-the-art results across datasets, which indicates that we need to select appropriate combinations depending on the dataset characteristics. In response, we propose a simple yet holistic classification method A2DUG which leverages all combinations of node representations in directed and undirected graphs. We demonstrate that A2DUG stably performs well on various datasets and improves the accuracy up to 11.29 compared with the state-of-the-art methods. To spur the development of new methods, we publicly release our complete codebase under the MIT license.

cs.LG↗