arXiv subjects

Yingze Li

Publications and source records attributed to Yingze Li.

8 recordsLinked to original sources

arXiv2026

Reward-Weighted On-Policy Distillation with an Open Property-Equivalence Verifier for NL-to-SVA Generation

LLM-based generation of SystemVerilog Assertions (SVA) is often reported as nearing saturation, with the strongest specialized model reaching ${\sim}76\%$ accuracy on NL2SVA-Human. We show that this aggregate hides a temporal gap: models that appear strong overall still collapse to a few implication templates on bounded-delay and liveness specifications. The core issue is that the dominant recipe, supervised fine-tuning on NL/SVA pairs, optimizes token-level mimicry rather than the \emph{property equivalence} that defines SVA correctness. We introduce \emph{Reward-Weighted On-Policy Distillation} (RWOPD), an on-policy distillation method that samples student rollouts, scores them with an open SymbiYosys+Z3 Property-Equivalence Checker (PEC), and applies a verifier-reward-weighted forward-KL gradient from a frozen 14B teacher on verifier-passable rollouts. This keeps the supervision dense at every response token while grounding both selection and loss weight in property-equivalent behavior. RWOPD distills CodeV-SVA-14B into a Qwen2.5-Coder-7B-Instruct student that sets a new state of the art on NL2SVA-Human and NL2SVA-Machine across pass@1, pass@5, and pass@10, surpassing both specialized prior SOTA models and 671B general-purpose baselines.

cs.AR↗

arXiv2025

ForeSight: A Predictive-Scheduling Deterministic Database

Deterministic databases enable scalable replicated systems by executing transactions in a predetermined order. However, existing designs fail to capture transaction dependencies, leading to insufficient scheduling, high abort rates, and poor resource utilization. By addressing these challenges with lightweight conflict prediction and informed scheduling, we present ForeSight, a high-performance deterministic database system. Our system has three core improvements: (1) We design an Association Sum-Product Network to predict potential transaction conflicts, providing the input for dependency analysis without pre-obtained read/write sets. (2) We enhance the storage engine to integrate multi-version-based optimization, improving the execution process and fallback strategy to boost commit rates and concurrency. (3) We propose a matrix two-pass forward scan algorithm that performs dependency analysis to generate conflict-aware schedules, significantly reducing scheduling overhead. Experimental results on multiple benchmarks show that ForeSight achieves up to 2 times higher throughput on skewed workloads and maintains strong performance under contention, demonstrating that predictive scheduling substantially improves deterministic database scalability.

cs.DB↗

arXiv2025

Algorithmic Complexity Attacks on All Learned Cardinality Estimators: A Data-centric Approach

Learned cardinality estimators show promise in query cardinality prediction, yet they universally exhibit fragility to training data drifts, posing risks for real-world deployment. This work is the first to theoretical investigate how minimal data-level drifts can maximally degrade the accuracy of learned estimators. We propose data-centric algorithmic complexity attacks against learned estimators in a black-box setting, proving that finding the optimal attack strategy is NP-Hard. To address this, we design a polynomial-time approximation algorithm with a $(1-\kappa)$ approximation ratio. Extensive experiments demonstrate our attack's effectiveness: on STATS-CEB and IMDB-JOB benchmarks, modifying just 0.8\% of training tuples increases the 90th percentile Qerror by three orders of magnitude and raises end-to-end processing time by up to 20$\times$. Our work not only reveals critical vulnerabilities in deployed learned estimators but also provides the first unified worst-case theoretical analysis of their fragility under data updates. Additionally, we identify two countermeasures to mitigate such black-box attacks, offering insights for developing robust learned database optimizers.

cs.DB↗

arXiv2025

DistJoin: A Decoupled Join Cardinality Estimator based on Adaptive Neural Predicate Modulation

Research on learned cardinality estimation has made significant progress in recent years. However, existing methods still face distinct challenges that hinder their practical deployment in production environments. We define these challenges as the ``Trilemma of Cardinality Estimation'', where learned cardinality estimation methods struggle to balance generality, accuracy, and updatability. To address these challenges, we introduce DistJoin, a join cardinality estimator based on efficient distribution prediction using multi-autoregressive models. Our contributions are threefold: (1) We propose a method to estimate join cardinality by leveraging the probability distributions of individual tables in a decoupled manner. (2) To meet the requirements of efficiency for DistJoin, we develop Adaptive Neural Predicate Modulation (ANPM), a high-throughput distribution estimation model. (3) We demonstrate that an existing similar approach suffers from variance accumulation issues by formal variance analysis. To mitigate this problem, DistJoin employs a selectivity-based approach to infer join cardinality, effectively reducing variance. In summary, DistJoin not only represents the first data-driven method to support both equi and non-equi joins simultaneously but also demonstrates superior accuracy while enabling fast and flexible updates. The experimental results demonstrate that DistJoin achieves the highest accuracy, robustness to data updates, generality, and comparable update and inference speed relative to existing methods.

cs.DB↗

arXiv2025

Brame: Hierarchical Data Management Framework for Cloud-Edge-Device Collaboration

In the realm of big data, cloud-edge-device collaboration is prevalent in industrial scenarios. However, a systematic exploration of the theory and methodologies related to data management in this field is lacking. This paper delves into the sub-problem of data storage and scheduling within cloud-edge-device collaborative environments. Following extensive research and analysis of the characteristics and requirements of data management in cloud-edge collaboration, it is evident that existing studies on hierarchical data management primarily focus on the migration of hot and cold data. Additionally, these studies encounter challenges such as elevated operational and maintenance costs, difficulties in locating data within tiered storage, and intricate metadata management attributable to excessively fine-grained management granularity. These challenges impede the fulfillment of the storage needs in cloud-edge-device collaboration. To overcome these challenges, we propose a \underline{B}lock-based hie\underline{R}archical d\underline{A}ta \underline{M}anagement fram\underline{E}work, \textbf{Brame}, which advocates for a workload-aware three-tier storage architecture and suggests a shift from using tuples to employing $Blocks$ as the fundamental unit for data management. \textbf{Brame} owns an offline block generation method designed to facilitate efficient block generation and expeditious query routing. Extensive experiments substantiate the superior performance of \textbf{Brame}.

cs.DB↗

arXiv2024

CONCERTO: Complex Query Execution Mechanism-Aware Learned Cost Estimation

With the growing demand for massive data analysis, many DBMSs have adopted complex underlying query execution mechanisms, including vectorized operators, parallel execution, and dynamic pipeline modifications. However, there remains a lack of targeted Query Performance Prediction (QPP) methods for these complex execution mechanisms and their interactions, as most existing approaches focus on traditional tree-shaped query plans and static serial executors. To address this challenge, this paper proposes CONCERTO, a Complex query executiON meChanism-awaE leaRned cosT estimatiOn method. CONCERTO first establishes independent resource cost models for each physical operator. It then constructs a Directed Acyclic Graph (DAG) consisting of a dataflow tree backbone and resource competition relationships among concurrent operators. After calibrating the cost impact of parallel operator execution using Graph Attention Networks (GATs) with additional attention mechanisms, CONCERTO extracts and aggregates cost vector trees through Temporal Convolutional Networks (TCNs), ultimately achieving effective query performance prediction. Experimental results demonstrate that CONCERTO achieves higher prediction accuracy than existing methods.

cs.DB↗

arXiv2024

Updateable Data-Driven Cardinality Estimator with Bounded Q-error

Modern Cardinality Estimators struggle with data updates. This research tackles this challenge within single-table. We introduce ICE, an Index-based Cardinality Estimator, the first data-driven estimator that enables instant, tuple-leveled updates. ICE has learned two key lessons from the multidimensional index and applied them to solve cardinality estimation in dynamic scenarios: (1) Index possesses the capability for swift training and seamless updating amidst vast multidimensional data. (2) Index offers precise data distribution, staying synchronized with the latest database version. These insights endow the index with the ability to be a highly accurate, data-driven model that rapidly adapts to data updates and is resilient to out-of-distribution challenges during query testing. To make a solitary index support cardinality estimation, we have crafted sophisticated algorithms for training, updating, and estimating, analyzing unbiasedness and variance. Extensive experiments demonstrate the superiority of ICE. ICE offers precise estimations and fast updates/construction across diverse workloads. Compared to state-of-the-art real-time query-driven models, ICE boasts superior accuracy (2-3 orders of magnitude more precise), faster updates (4.7-6.9 times faster), and significantly reduced training time (up to 1-3 orders of magnitude faster).

cs.DB↗

arXiv2023

One stone, two birds: A lightweight multidimensional learned index with cardinality support

Innovative learning based structures have recently been proposed to tackle index and cardinality estimation tasks, specifically learned indexes and data driven cardinality estimators. These structures exhibit excellent performance in capturing data distribution, making them promising for integration into AI driven database kernels. However, accurate estimation for corner case queries requires a large number of network parameters, resulting in higher computing resources on expensive GPUs and more storage overhead. Additionally, the separate implementation for CE and learned index result in a redundancy waste by storage of single table distribution twice. These present challenges for designing AI driven database kernels. As in real database scenarios, a compact kernel is necessary to process queries within a limited storage and time budget. Directly integrating these two AI approaches would result in a heavy and complex kernel due to a large number of network parameters and repeated storage of data distribution parameters. Our proposed CardIndex structure effectively killed two birds with one stone. It is a fast multidim learned index that also serves as a lightweight cardinality estimator with parameters scaled at the KB level. Due to its special structure and small parameter size, it can obtain both CDF and PDF information for tuples with an incredibly low latency of 1 to 10 microseconds. For tasks with low selectivity estimation, we did not increase the model's parameters to obtain fine grained point density. Instead, we fully utilized our structure's characteristics and proposed a hybrid estimation algorithm in providing fast and exact results.

cs.DB↗