Secure multi-party computation techniques enable in-depth analysis on joint graphs that inherently encompass comprehensive topology information and extended attributes, while preserving data privacy. In the two-party setting, existing approaches suffer from inefficiencies due to redundant secure sorting or costly secure shuffling operations required for secure message passing. Some works improve efficiency by relaxing security assumptions, either through differential privacy or by introducing helper parties.

Encrypted matrix-vector multiplication is a fundamental component of a variety of applications that involve data privacy concerns. Current algorithms utilizing fully homomorphic encryption (FHE) generally use batching to enhance computational efficiency while neglecting the sparsity of the matrices, a characteristic that exists naturally in many practical situations. Alternatively, porting plaintext algorithms that skip zero elements to address sparsity may fail to utilize batching and introduce additional privacy concerns.

Accurate acquisition of surface meteorological conditions at arbitrary locations holds significant importance for weather forecasting and climate simulation. Meteorological states derived from satellite observations are often provided in the form of low-resolution grid fields. If spatial interpolation is applied directly to obtain meteorological states for specific locations, there will often be significant discrepancies compared to actual observations. Existing downscaling methods for acquiring meteorological state information at higher resolutions commonly overlook the correlation with satellite observations. To bridge the gap, we propose Satellite-observations Guided Diffusion Model (SGD), a conditional diffusion model pre-trained on ERA5 reanalysis data with satellite observations (GridSat) as conditions, which is employed for sampling downscaled meteorological states through a zero-shot guided sampling strategy and patch-based methods. During the training process, we propose to fuse the information from GridSat satellite observations into ERA5 maps via the attention mechanism, enabling SGD to generate atmospheric states that align more accurately with actual conditions. In the sampling, we employed optimizable convolutional kernels to simulate the upscale process, thereby generating high-resolution ERA5 maps using low-resolution ERA5 maps as well as observations from weather stations as guidance. Moreover, our devised patch-based method promotes SGD to generate meteorological states at arbitrary resolutions. Experiments demonstrate SGD fulfills accurate meteorological states downscaling to 6.25km. The code is available at https://github.com/Tusiwei/SGD

Precipitation nowcasting plays a pivotal role in socioeconomic sectors, especially in severe convective weather warnings. Although notable progress has been achieved by approaches mining the spatiotemporal correlations with deep learning, these methods still suffer severe blurriness as the lead time increases, which hampers accurate predictions for extreme precipitation. To alleviate blurriness, researchers explore generative methods conditioned on blurry predictions. However, the pairs of blurry predictions and corresponding ground truth need to be given in advance, making the training pipeline cumbersome and limiting the generality of generative models within blurry modes that appear in training data. By rethinking the blurriness in precipitation nowcasting as a blur kernel acting on predictions, we propose an unsupervised postprocessing method to eliminate the blurriness without the requirement of training with the pairs of blurry predictions and corresponding ground truth. Specifically, we utilize blurry predictions to guide the generation process of a pre-trained unconditional denoising diffusion probabilistic model (DDPM) to obtain high-fidelity predictions with eliminated blurriness. A zero-shot blur kernel estimation mechanism and an auto-scale denoise guidance strategy are introduced to adapt the unconditional DDPM to any blurriness modes varying from datasets and lead times in precipitation nowcasting. Extensive experiments are conducted on 7 precipitation radar datasets, demonstrating the generality and superiority of our method.

Data assimilation (DA) is an essential statistical technique for generating accurate estimates of a physical system's states by combining prior model predictions with observational data, especially in the realm of weather forecasting. Effectively modeling the prior distribution while adapting to diverse observational sources presents significant challenges for both traditional and neural network-based DA algorithms. This paper introduces VAE-Var, a novel neural network-based data assimilation algorithm aimed at 1) enhancing accuracy by capturing the non-Gaussian characteristics of the conditional background distribution $p(\mathbf{x}|\mathbf{x}_b)$, and 2) efficiently assimilating real-world observational data. VAE-Var utilizes a variational autoencoder to learn the background error distribution, with its decoder creating a variational cost function to optimize the analysis states. The advantages of VAE-Var include: 1) it maintains the framework of traditional variational assimilation, enabling it to accommodate various observation operators, particularly irregular observations; 2) it lessens the dependence on expert knowledge for constructing the background distribution, allowing for improved modeling of non-Gaussian structures; and 3) experimental results indicate that, when applied to the FengWu weather forecasting model, VAE-Var outperforms DiffDA and two traditional algorithms (interpolation and 3DVar) in terms of assimilation accuracy in sparse observational contexts, and is capable of assimilating real-world GDAS prepbufr observations over a year.

Pair-then-Aggregate (PtA) introduces a programming paradigm and an automated parallel execution engine for large-scale secure multi-party (MPC) computations, drawing inspiration from the widely-used yet not explicitly defined Table-Generation-and-Look-up (TGL) pattern in privacy-preserving algorithm design. PtA offers an easy-to-use API and a versatile execution engine that harnesses various levels of parallelism and adapts to different MPC deployments, algorithms, and input sizes. Evaluations on a real-world MPC platform demonstrate significant enhancements in scalability, adaptability, and ease of programming. PtA can process one billion input elements with 3-23 lines of C++ code in 5-74 seconds. It outperforms state-of-the-art implementations in 91.4 % of 35 test cases, achieving up to a$12.4 \times$speedup with much less coding effort.11Our code is provided in https://github.com/Fannxy/Pair-then-Aggregate

Weather prediction is a critical task for human society, where impressive progress has been made by training artificial intelligence weather prediction (AIWP) methods with reanalysis data. However, reliance on reanalysis data limits the AIWPs with shortcomings, including data assimilation biases and temporal discrepancies. To liberate AIWPs from the reanalysis data, observation forecasting emerges as a transformative paradigm for weather prediction. One of the key challenges in observation forecasting is learning spatiotemporal dynamics across disparate measurement systems with irregular high-resolution observation data, which constrains the design and prediction of AIWPs. To this end, we propose our DAWP as an innovative framework to enable AIWPs to operate in a complete observation space by initialization with an artificial intelligence data assimilation (AIDA) module. Specifically, our AIDA module applies a mask multi-modality autoencoder (MMAE) for assimilating irregular satellite observation tokens encoded by mask ViT-VAEs. For AIWP, we introduce a spatiotemporal decoupling transformer with cross-regional boundary conditioning (CBC), learning the dynamics in observation space, to enable sub-image-based global observation forecasting. Comprehensive experiments demonstrate that AIDA initialization significantly improves the roll-out and efficiency of AIWP. Additionally, we show that DAWP holds promising potential to be applied in global precipitation forecasting.

Data assimilation (DA) aims to estimate the full state of a dynamical system by combining partial and noisy observations with a prior model forecast, commonly referred to as the background. In atmospheric applications, this problem is fundamentally ill-posed due to the sparsity of observations relative to the high-dimensional state space. Traditional methods address this challenge by simplifying background priors to regularize the solution, which are empirical and require continual tuning for application. Inspired by alignment techniques in text-to-image diffusion models, we propose Align-DA, which formulates DA as a generative process and uses reward signals to guide background priors—replacing manual tuning with data-driven alignment. Specifically, we train a score-based model in the latent space to approximate the background-conditioned prior, and align it using three complementary reward signals for DA: (1) assimilation accuracy, (2) forecast skill initialized from the assimilated state, and (3) physical adherence of the analysis fields. Experiments with multiple reward signals demonstrate consistent improvements in analysis quality across different evaluation metrics and observation-guidance strategies. These results show that preference alignment, implemented as a soft constraint, can automatically adapt complex background priors tailored to DA, offering a promising new direction for advancing the field.

Accurate estimation of background error (i.e., forecast error) distribution is critical for effective data assimilation (DA) in numerical weather prediction (NWP). In state-of-the-art operational DA systems, it is common to account for the temporal evolution of background errors by employing hybrid methods, which blend a static climatological covariance with a flow-dependent ensemble-derived component. While effective to some extent, these methods typically assume Gaussian-distributed errors and rely heavily on hand-crafted covariance structures and domain expertise, limiting their ability to capture the complex, non-Gaussian nature of atmospheric dynamics. In this work, we propose LoRA-EnVar, a novel hybrid ensemble variational DA algorithm that integrates low-rank adaptation (LoRA) into a deep generative modeling framework. We first learn a climatological background error distribution using a variational autoencoder (VAE) trained on historical data. To incorporate flow-dependent uncertainty, we introduce LoRA modules that efficiently adapt the learned distribution in response to flow-dependent ensemble perturbations. Our approach supports online finetuning, enabling dynamic updates of the background error distribution without catastrophic forgetting. We validate LoRA-EnVar in high-resolution assimilation settings using the FengWu forecast model and simulated observations from ERA5 reanalysis. Experimental results show that LoRA-EnVar significantly improves assimilation accuracy over models assuming static background error distribution and achieves comparable or better performance than full finetuning while reducing the number of trainable parameters by three orders of magnitude. This demonstrates the potential of parameter-efficient adaptation for scalable, non-Gaussian DA in operational meteorology.

Ego-centric queries, focusing on a target vertex and its direct neighbors, are essential for various applications. Enabling such queries on graphs owned by mutually distrustful data providers without breaching privacy holds promise for more comprehensive results. In this paper, we propose GORAM, a graph-oriented data structure that enables efficient ego-centric queries on federated graphs with strong privacy guarantees. GORAM leverages secure multiparty computation (MPC) and ensures that no information about the graphs or the querying keys is exposed during the process. For practical performance, GORAM partitions the federated graph and constructs an Oblivious RAM (ORAM )-inspired index atop these partitions. This design enables each ego-centric query to process only a single partition, which can be accessed fast and securely. Utilizing GORAM, we develop a prototype querying engine on a real-world MPC framework. We then conduct a comprehensive evaluation using five commonly used queries similar to the LinkBench workload description [11] on both synthetic and real-world graphs. Our evaluation shows that all five queries can be completed in just 58.1 milliseconds to 35.7 seconds, even on graphs with up to 41.6 million vertices and 1.4 billion edges. To the best of our knowledge, this represents the first instance of processing billion-scale graphs with practical performance on MPC.

2-hop labeling has been widely utilized to accelerate the efficiency of online shortest distance queries. Given the nature of frequent changes in real-world graphs, the efficient maintenance of 2-hop labeling index has been extensively studied recently. However, existing methods cannot efficiently process large-scale graphs due to their high time and memory costs, and most of them process large batches of updates sequentially, significantly decreasing efficiency. In this paper, we propose a novel algorithm for maintaining the 2-hop labeling index in a parallel manner, called M2HL , which can efficiently handle both edge insertions and deletions. Moreover, we theoretically prove that M2HL maintains both correctness and minimality for the updated 2-hop labeling index. Our experiments on ten large-scale graphs demonstrate that M2HL outperforms the state-of-the-art 2-hop labeling maintenance methods by up to four orders of magnitude in speed while maintaining correctness and minimality, as well as exhibiting strong scalability and low memory usage.

Enabling various parties to share data enhances online fraud detection capabilities considering fraudsters tend to reuse resources attacking multiple platforms. Multi-party computation (MPC) techniques, such as secret sharing, offer potential privacy-preserving solutions but face efficiency challenges when handling large-scale data. This paper presents a novel approach, SecureFD (Secure Fraud Detector), aimed at detecting fraud in multi-party graph data, ensuring privacy, accuracy, and scalability. We propose a graph neural network EPR-GNN, which is MPC-friendly, as the base detector. Then we design a framework that allows multiple parties to train EPR-GNN collaboratively on secure sparse graphs in a privacy- preserving manner. The oblivious node embedding sharing protocol in the collaborative training procedure achieves up to a 45× speed-up, supporting over four million users compared to the naive solution. Additionally, we further reduce secure computation by locally pruning a significant number of non-suspicious users and selecting only the most valuable resources for sharing. Experiments on real datasets demonstrate that by securely integrating data from different parties, SecureFD achieves superior detection performance compared to state-of-the-art local detectors. And the local pruning greatly improves the scalability without compromising detection accuracies.

Data-driven weather forecasting models are advancing rapidly, yet they rely on initial states (i.e., analysis states) typically produced by traditional data assimilation algorithms. Four-dimensional variational assimilation (4DVar) is one of the most widely adopted data assimilation algorithms in numerical weather prediction centers; it is accurate but computationally expensive. In this paper, we aim to couple the AI forecasting model, FengWu, with 4DVar to build a self-contained data-driven global weather forecasting framework, FengWu-4DVar. To achieve this, we propose an *AI-embedded* 4DVar algorithm that includes three components: (1) a 4DVar objective function embedded with the FengWu forecasting model and its error representation to enhance efficiency and accuracy; (2) a spherical-harmonic-transform-based (SHT-based) approximation strategy for capturing the horizontal correlation of background error; and (3) an auto-differentiation (AD) scheme for determining the optimal analysis fields. Experimental results show that under the ERA5 simulated observational data with varying proportions and noise levels, FengWu-4DVar can generate accurate analysis fields; remarkably, it has achieved stable self-contained global weather forecasts for an entire year for the first time, demonstrating its potential for real-world applications. Additionally, our framework is approximately 100 times faster than the traditional 4DVar algorithm under similar experimental conditions, highlighting its significant computational efficiency.

Data assimilation is a vital component in modern global medium-range weather forecasting systems to obtain the best estimation of the atmospheric state by combining the short-term forecast and observations. Recently, AI-based data assimilation approaches have attracted increasing attention for their significant advantages over traditional techniques in terms of computational consumption. However, existing AI-based data assimilation methods can only handle observations with a specific resolution, lacking the compatibility and generalization ability to assimilate observations with other resolutions. Considering that complex real-world observations often have different resolutions, we propose the Fourier Neural Processes (FNP) for arbitrary-resolution data assimilation in this paper. Leveraging the efficiency of the designed modules and flexible structure of neural processes, FNP achieves state-of-the-art results in assimilating observations with varying resolutions, and also exhibits increasing advantages over the counterparts as the resolution and the amount of observations increase. Moreover, our FNP trained on a fixed resolution can directly handle the assimilation of observations with out-of-distribution resolutions and the observational information reconstruction task without additional fine-tuning, demonstrating its excellent generalization ability across data resolutions as well as across tasks. Code is available at https://github.com/OpenEarthLab/FNP.

Due to the absence of a library for non-linear function evaluation, so-called general-purpose secure multi-party computation (MPC) are not as "general'' as MPC programmers expect. Prior arts either naively reuse plaintext methods, resulting in suboptimal performance and even incorrect results, or handcraft ad hoc approximations for specific functions or platforms. We propose a general technique, NFGen1, that utilizes pre-computed discrete piecewise polynomials to accurately approximate generic functions using fixed-point numbers. We implement it using a performance-prediction-based code generator to support different platforms. Conducting extensive evaluations of 23 non-linear functions against six MPC protocols on two platforms, we demonstrate significant performance, accuracy, and generality improvements over existing methods.

The web link selection problem is to select a small subset of web links from a large web link pool, and to place the selected links on a web page that can only accommodate a limited number of links, e.g., advertisements, recommendations, or news feeds. Despite the long concerned click-through rate which reflects the attractiveness of the link itself, revenue can only be obtained from user actions after clicks, e.g., purchasing after being directed to the product pages by recommendation links. Thus, web links have an intrinsic multi-level feedback structure. With this observation, we consider the context-free web link selection problem, where the objective is to maximize revenue while ensuring that the attractiveness is no less than a preset threshold. The key challenge of the problem is that each link's multi-level feedbacks are stochastic, and unobservable unless the link is selected. We model this problem with a constrained stochastic multi-armed bandit formulation, and design an efficient link selection algorithm, called Constrained Upper Confidence Bound algorithm (Con-UCB). We prove O(sqrt(T ln(T))) bounds on both regret and violation of the attractiveness constraint. We also conduct extensive experiments on three real-world datasets, and show that Con-UCB outperforms state-of-the-art context-free bandit algorithms concerning the multi-level feedback structure.

Motivated by the increasing importance of providing delay-guaranteed services in general computing and communication systems, and the recent wide adoption of learning and prediction in network control, in this work, we consider a general stochastic single-server multi-user system and investigate the fundamental benefit of predictive scheduling in improving timely-throughput, being the rate of packets that are delivered to destinations before their deadlines. By adopting an error rate-based prediction model, we first derive a Markov decision process (MDP) solution to optimize the timely-throughput objective subject to an average resource consumption constraint. Based on a packet-level decomposition of the MDP, we explicitly characterize the optimal scheduling policy and rigorously quantify the timely-throughput improvement due to predictive-service, which scales as Θ(p[C1[((a-amaxq))/(p-q)] ρτ+ C2(1-[1/p])](1-ρD)), where a, amax, ρ ∈ (0,1), C1> 0, C2≥ 0 are constants, p is the true-positive rate in prediction, Q is the false-negative rate, τ is the packet deadline and D is the prediction window size. We also conduct extensive simulations to validate our theoretical findings. Our results provide novel insights into how prediction and system parameters impact performance and provide useful guidelines for designing predictive low-latency control algorithms.

Motivated by the increasing importance of providing delay-guaranteed services in general computing and communication systems, and the recent wide adoption of learning and prediction in network control, in this paper, we consider a general stochastic single-server multi-user system and investigate the fundamental benefit of predictive scheduling in improving timely-throughput, being the rate of packets that are delivered to destinations before their deadlines. By adopting an error rate based prediction model, we first derive a Markov decision process (MDP) solution to optimize the timely-throughput objective subject to an average resource consumption constraint. Based on a packet-level decomposition of the MDP, we explicitly characterize the optimal scheduling policy and rigorously quantify the timely-throughput improvement due to predictive-service, which scales as Θ(p[C1(a - amaxq)ρτ/(p -q)+C2(1-(1/p)](1-ρD)), where a, amax, ρ ∈ (0, 1), C1> 0, C2≥ 0 are constants, p is the true-positive rate in prediction, q is the false-negative rate, r is the packet deadline, and D is the prediction window size. We also conduct extensive simulations to validate our theoretical findings. Our results provide novel insights into how prediction and system parameters impact performance and provide useful guidelines for designing predictive low-latency control algorithms.

Selecting the right web links for a website is important because appropriate links not only can provide high attractiveness but can also increase the website's revenue. In this work, we first show that web links have an intrinsic multi-level feedback structure. For example, consider a 2-level feedback web link: the 1st level feedback provides the Click-Through Rate (CTR) and the 2nd level feedback provides the potential revenue, which collectively produce the compound 2-level revenue. We consider the context-free links selection problem of selecting links for a homepage so as to maximize the total compound 2-level revenue while keeping the total 1st level feedback above a preset threshold. We further generalize the problem to links with n (n ≥ 2)-level feedback structure. The key challenge is that the links' multi-level feedback structures are unobservable unless the links are selected on the homepage. To our best knowledge, we are the first to model the links selection problem as a constrained multi-armed bandit problem and design an effective links selection algorithm by learning the links' multi-level structure with provable sub-linear regret and violation bounds. We uncover the multi-level feedback structures of web links in two real-world datasets. We also conduct extensive experiments on the datasets to compare our proposed LExp algorithm with two state-of-the-art context-free bandit algorithms and demonstrate that LExp algorithm is the most effective in links selection while satisfying the constraint.

We consider the peak age-of-information (PAoI) in an M/M/1 queueing system with packet delivery error, i.e., update packets can get lost during transmissions to their destination. We focus on two types of policies, one is to adopt Last-Come-First-Served (LCFS) scheduling, and the other is to utilize retransmissions, i.e., keep transmitting the most recent packet. Both policies can effectively avoid the queueing delay of a busy channel and ensure a small PAoI. Exact PAoI expressions under both policies with different error probabilities are derived, including First-Come-First-Served (FCFS), LCFS with preemptive priority, LCFS with non-preemptive priority, Retransmission with preemptive priority, and Retransmission with non-preemptive priority. Numerical results obtained from analysis and simulation are presented to validate our results.