arXiv subjects

Haoze Song

Publications and source records attributed to Haoze Song.

13 recordsLinked to original sources

arXiv2026

BubbleRAG: Evidence-Driven Retrieval-Augmented Generation for Black-Box Knowledge Graphs

Large Language Models (LLMs) exhibit hallucinations in knowledge-intensive tasks. Graph-based retrieval augmented generation (RAG) has emerged as a promising solution, yet existing approaches suffer from fundamental recall and precision limitations when operating over black-box knowledge graphs -- graphs whose schema and structure are unknown in advance. We identify three core challenges that cause recall loss (semantic instantiation uncertainty and structural path uncertainty) and precision loss (evidential comparison uncertainty). To address these challenges, we formalize the retrieval task as the Optimal Informative Subgraph Retrieval (OISR) problem -- a variant of Group Steiner Tree -- and prove it to be NP-hard and APX-hard. We propose BubbleRAG, a training-free pipeline that systematically optimizes for both recall and precision through semantic anchor grouping, heuristic bubble expansion to discover candidate evidence graphs (CEGs), composite ranking, and reasoning-aware expansion. Experiments on multi-hop QA benchmarks demonstrate that BubbleRAG achieves state-of-the-art results, outperforming strong baselines in both F1 and accuracy while remaining plug-and-play.

cs.IR↗

arXiv2026

Structure-Aware Epistemic Uncertainty Quantification for Neural Operator PDE Surrogates

Neural operators (NOs) provide fast, resolution-invariant surrogates for mapping input fields to PDE solution fields, but their predictions can exhibit significant epistemic uncertainty due to finite data, imperfect optimization, and distribution shift. For practical deployment in scientific computing, uncertainty quantification (UQ) must be both computationally efficient and spatially faithful, i.e., uncertainty bands should align with the localized residual structures that matter for downstream risk management. We propose a structure-aware epistemic UQ scheme that exploits the modular anatomy common to modern NOs (lifting-propagation-recovering). Instead of applying unstructured weight perturbations (e.g., naive dropout) across the entire network, we restrict Monte Carlo sampling to a module-aligned subspace by injecting stochasticity only into the lifting module, and treat the learned solver dynamics (propagation and recovery) as deterministic. We instantiate this principle with two lightweight lifting-level perturbations, including channel-wise multiplicative feature dropout and a Gaussian feature perturbation with matched variance, followed by standard calibration to construct uncertainty bands. Experiments on challenging PDE benchmarks (including discontinuous-coefficient Darcy flow and geometry-shifted 3D car CFD surrogates) demonstrate that the proposed structure-aware design yields more reliable coverage, tighter bands, and improved residual-uncertainty alignment compared with common baselines, while remaining practical in runtime.

cs.LG↗

arXiv2025

RRTO: A High-Performance Transparent Offloading System for Model Inference in Mobile Edge Computing

Deploying Machine Learning (ML) applications on resource-constrained mobile devices remains challenging due to limited computational resources and poor platform compatibility. While Mobile Edge Computing (MEC) offers offloading-based inference paradigm using GPU servers, existing approaches are divided into non-transparent and transparent methods, with the latter necessitating modifications to the source code. Non-transparent offloading achieves high performance but requires intrusive code modification, limiting compatibility with diverse applications. Transparent offloading, in contrast, offers wide compatibility but introduces significant transmission delays due to per-operator remote procedure calls (RPCs). To overcome this limitation, we propose RRTO, the first high-performance transparent offloading system tailored for MEC inference. RRTO introduces a record/replay mechanism that leverages the static operator sequence in ML models to eliminate repetitive RPCs. To reliably identify this sequence, RRTO integrates a novel Operator Sequence Search algorithm that detects repeated patterns, filters initialization noise, and accelerates matching via a two-level strategy. Evaluation demonstrates that RRTO achieves substantial reductions of up to 98% in both per-inference latency and energy consumption compared to state-of-the-art transparent methods and yields results comparable to non-transparent approaches, all without necessitating any source code modification.

cs.NI↗

arXiv2025

Reformulating Neural Operators in $d+1$ Dimensions for Embedding Evolution

Neural Operators (NOs) are powerful architectures for learning mappings between function spaces. While most advances focus on refining kernel parameterizations over the $d$-dimensional physical domain, the evolution of lifted embeddings remains underexplored, which often drives models toward computationally expensive embedding-scaling designs to improve approximation. In this paper, we introduce an auxiliary function dimension that models embedding evolution in operator form, thereby reformulating the NO pipeline in $d+1$ dimensions. We instantiate this framework via Fourier-based operators acting jointly on the physical and auxiliary domains, yielding a basis-diversified auxiliary evolution module as an alternative to brute-force embedding scaling. Across more than ten increasingly challenging benchmarks, ranging from the 1D heat equation to the highly nonlinear 3D Rayleigh-Taylor instability, our model consistently achieves the lowest relative $L_2$ error among the evaluated baselines. Crucially, this advantage is empirically supported by (1) controlled budget-aware comparisons against scaled and ablated baselines; (2) robustness under mixed-resolution training and super-resolution inference; and (3) zero-shot generalization to unseen temporal regimes. In addition, we present a broader set of design choices for lifting and recovery operators, demonstrating their impact on our model's predictive performance.

cs.LG↗

arXiv2025

Parameter estimation of structural dynamics with neural operators enabled surrogate modeling

Parameter estimation in structural dynamics generally involves inferring the values of physical, geometric, or even customized parameters based on first principles or expert knowledge, which is challenging for complex structural systems. In this work, we present a unified deep learning-based framework for parameterization, forward modeling, and inverse modeling of structural dynamics. The parameterization is flexible and can be user-defined, including physical and/or non-physical (customized) parameters. In the forward modeling, we train a neural operator for response prediction -- forming a surrogate model, which leverages the defined system parameters and excitation forces as inputs to the model. The inverse modeling focuses on estimating system parameters. In particular, the learned forward surrogate model (which is differentiable) is utilized for preliminary parameter estimation via gradient-based optimization; to further boost the parameter estimation, we introduce a neural refinement method to mitigate ill-posed problems, which often occur in the former. The framework's effectiveness is verified numerically and experimentally, in both interpolation and extrapolation cases, indicating its capability to capture intrinsic dynamics of structural systems from both forward and inverse perspectives. Moreover, the framework's flexibility is expected to support a wide range of applications, including surrogate modeling, structural identification, damage detection, and inverse design of structural systems.

cs.CE↗

arXiv2025

K2: On Optimizing Distributed Transactions in a Multi-region Data Store with TrueTime Clocks (Extended Version)

TrueTime clocks (TTCs) that offer accurate and reliable time within limited uncertainty bounds have been increasingly implemented in many clouds. Multi-region data stores that seek decentralized synchronization for high performance represent an ideal application of TTC. However, the co-designs between the two were often undervalued or failed to realize their full potential. This paper proposes K2, a multi-region data store that intensely explores the opportunity of using TTC for distributed transactions. Compared to its pioneer, Google Spanner, K2 augments TTC's semantics in three core design pillars. First, K2 carries a new timestamp-generating scheme that is capable of providing a small time uncertainty bound at scale. Second, K2 revitalizes existing multi-version timestamp-ordered concurrency control to realize multi-version properties for read-write transactions. Third, K2 introduces a new TTC-based visibility control protocol that provides efficient reads at replicas. Our evaluation shows that, K2 achieves an order of magnitude higher transaction throughput relative to other practical geo-distributed transaction protocols while ensuring a lower visibility delay at asynchronous replicas.

cs.DB↗

arXiv2025

Harnessing Scale and Physics: A Multi-Graph Neural Operator Framework for PDEs on Arbitrary Geometries

Partial Differential Equations (PDEs) underpin many scientific phenomena, yet traditional computational approaches often struggle with complex, nonlinear systems and irregular geometries. This paper introduces the AMG method, a Multi-Graph neural operator approach designed for efficiently solving PDEs on Arbitrary geometries. AMG leverages advanced graph-based techniques and dynamic attention mechanisms within a novel GraphFormer architecture, enabling precise management of diverse spatial domains and complex data interdependencies. By constructing multi-scale graphs to handle variable feature frequencies and a physics graph to encapsulate inherent physical properties, AMG significantly outperforms previous methods, which are typically limited to uniform grids. We present a comprehensive evaluation of AMG across six benchmarks, demonstrating its consistent superiority over existing state-of-the-art models. Our findings highlight the transformative potential of tailored graph neural operators in surmounting the challenges faced by conventional PDE solvers. Our code and datasets are available on https://github.com/lizhihao2022/AMG.

cs.LG↗

arXiv2024

Automated machine learning for physics-informed convolutional neural networks

Recent advances in deep learning for solving partial differential equations (PDEs) have introduced physics-informed neural networks (PINNs), which integrate machine learning with physical laws. Physics-informed convolutional neural networks (PICNNs) extend PINNs by leveraging CNNs for enhanced generalization and efficiency. However, current PICNNs depend on manual design, and inappropriate designs may not effectively solve PDEs. Furthermore, due to the diversity of physical problems, the ideal network architectures and loss functions vary across different PDEs. It is impractical to find the optimal PICNN architecture and loss function for each specific physical problem through extensive manual experimentation. To surmount these challenges, this paper uses automated machine learning (AutoML) to automatically and efficiently search for the loss functions and network architectures of PICNNs. We introduce novel search spaces for loss functions and network architectures and propose a two-stage search strategy. The first stage focuses on searching for factors and residual adjustment operations that influence the loss function, while the second stage aims to find the best CNN architecture. Experimental results show that our automatic searching method significantly outperforms the manually-designed model on multiple datasets.

cs.CE↗

arXiv2024

Hybrid-Parallel: Achieving High Performance and Energy Efficient Distributed Inference on Robots

The rapid advancements in machine learning techniques have led to significant achievements in various real-world robotic tasks. These tasks heavily rely on fast and energy-efficient inference of deep neural network (DNN) models when deployed on robots. To enhance inference performance, distributed inference has emerged as a promising approach, parallelizing inference across multiple powerful GPU devices in modern data centers using techniques such as data parallelism, tensor parallelism, and pipeline parallelism. However, when deployed on real-world robots, existing parallel methods fail to provide low inference latency and meet the energy requirements due to the limited bandwidth of robotic IoT. We present Hybrid-Parallel, a high-performance distributed inference system optimized for robotic IoT. Hybrid-Parallel employs a fine-grained approach to parallelize inference at the granularity of local operators within DNN layers (i.e., operators that can be computed independently with the partial input, such as the convolution kernel in the convolution layer). By doing so, Hybrid-Parallel enables different operators of different layers to be computed and transmitted concurrently, and overlap the computation and transmission phases within the same inference task. The evaluation demonstrate that Hybrid-Parallel reduces inference time by 14.9% ~41.1% and energy consumption per inference by up to 35.3% compared to the state-of-the-art baselines.

cs.RO↗

arXiv2023

PolarDB-IMCI: A Cloud-Native HTAP Database System at Alibaba

Cloud-native databases have become the de-facto choice for mission-critical applications on the cloud due to the need for high availability, resource elasticity, and cost efficiency. Meanwhile, driven by the increasing connectivity between data generation and analysis, users prefer a single database to efficiently process both OLTP and OLAP workloads, which enhances data freshness and reduces the complexity of data synchronization and the overall business cost. In this paper, we summarize five crucial design goals for a cloud-native HTAP database based on our experience and customers' feedback, i.e., transparency, competitive OLAP performance, minimal perturbation on OLTP workloads, high data freshness, and excellent resource elasticity. As our solution to realize these goals, we present PolarDB-IMCI, a cloud-native HTAP database system designed and deployed at Alibaba Cloud. Our evaluation results show that PolarDB-IMCI is able to handle HTAP efficiently on both experimental and production workloads; notably, it speeds up analytical queries up to $\times149$ on TPC-H (100 $GB$). PolarDB-IMCI introduces low visibility delay and little performance perturbation on OLTP workloads (< 5%), and resource elasticity can be achieved by scaling out in tens of seconds.

cs.DB↗

arXiv2022

Large-scale single-photon imaging

Benefiting from its single-photon sensitivity, single-photon avalanche diode (SPAD) array has been widely applied in various fields such as fluorescence lifetime imaging and quantum computing. However, large-scale high-fidelity single-photon imaging remains a big challenge, due to the complex hardware manufacture craft and heavy noise disturbance of SPAD arrays. In this work, we introduce deep learning into SPAD, enabling super-resolution single-photon imaging over an order of magnitude, with significant enhancement of bit depth and imaging quality. We first studied the complex photon flow model of SPAD electronics to accurately characterize multiple physical noise sources, and collected a real SPAD image dataset (64 $\times$ 32 pixels, 90 scenes, 10 different bit depth, 3 different illumination flux, 2790 images in total) to calibrate noise model parameters. With this real-world physical noise model, we for the first time synthesized a large-scale realistic single-photon image dataset (image pairs of 5 different resolutions with maximum megapixels, 17250 scenes, 10 different bit depth, 3 different illumination flux, 2.6 million images in total) for subsequent network training. To tackle the severe super-resolution challenge of SPAD inputs with low bit depth, low resolution, and heavy noise, we further built a deep transformer network with a content-adaptive self-attention mechanism and gated fusion modules, which can dig global contextual features to remove multi-source noise and extract full-frequency details. We applied the technique on a series of experiments including macroscopic and microscopic imaging, microfluidic inspection, and Fourier ptychography. The experiments validate the technique's state-of-the-art super-resolution SPAD imaging performance, with more than 5 dB superiority on PSNR compared to the existing methods.

physics.optics↗

arXiv2020

Efficient and DoS-resistant Consensus for Permissioned Blockchains

Existing permissioned blockchain systems designate a fixed and explicit group of committee nodes to run a consensus protocol that confirms the same sequence of blocks among all nodes. Unfortunately, when such a permissioned blockchain runs in a large scale on the Internet, these explicit committee nodes can be easily turned down by denial-of-service (DoS) or network partition attacks. Although work proposes scalable BFT protocols that run on a larger number of committee nodes, their efficiency drops dramatically when only a small number of nodes are attacked. In this paper, our EGES protocol leverages Intel SGX to develop a new abstraction called "stealth committee", which effectively hides the committee nodes into a large pool of fake committee nodes. EGES selects a distinct group of stealth committee for each block and confirms the same sequence of blocks among all nodes with overwhelming probability. Evaluation on typical geo-distributed settings shows that: (1)EGES is the first permissioned blockchain's consensus protocol that can tolerate tough DoS and network partition attacks; and (2) EGES achieves comparable throughput and latency as existing permissioned blockchains' protocols

cs.DC↗

arXiv2019

Optimizing Quantum Programs against Decoherence: Delaying Qubits into Quantum Superposition

Quantum computing technology has reached a second renaissance in the last decade. However, in the NISQ era pointed out by John Preskill in 2018, quantum noise and decoherence, which affect the accuracy and execution effect of quantum programs, cannot be ignored and corrected by the near future NISQ computers. In order to let users more easily write quantum programs, the compiler and runtime system should consider underlying quantum hardware features such as decoherence. To address the challenges posed by decoherence, in this paper, we propose and prototype QLifeReducer to minimize the qubit lifetime in the input OpenQASM program by delaying qubits into quantum superposition. QLifeReducer includes three core modules, i.e.,the parser, parallelism analyzer and transformer. It introduces the layered bundle format to express the quantum program, where a set of parallelizable quantum operations is packaged into a bundle. We evaluate quantum programs before and after transformed by QLifeReducer on both real IBM Q 5 Tenerife and the self-developed simulator. The experimental results show that QLifeReducer reduces the error rate of a quantum program when executed on IBMQ 5 Tenerife by 11%; and can reduce the longest qubit lifetime as well as average qubit lifetime by more than 20% on most quantum workloads.

quant-ph↗