Sparse General Matrix–Matrix Multiplication (SpGEMM) is a fundamental but computationally intensive operation that underpins many scientific workloads, including numerous AI applications. With the increasing demands for data security, privacy-preserving computation techniques, such as Fully Homomorphic Encryption (FHE), have gained significant attention for their ability to process sensitive data without decryption. Nonetheless, executing SpGEMM within the framework of FHE presents significant challenges. The most effective SpGEMM algorithms exploit matrix sparsity to minimize computational costs; however, FHE obscures both the data values and the sparsity structures. Prior FHE‑based privacy‑preserving computation frameworks either ignore the inherent sparsity of matrices and rely on dense General Matrix–Matrix Multiplication (GEMM), incurring substantial overhead from redundant homomorphic multiplications, or they attempt to exploit sparsity by encrypting only the non‑zero values, which inadvertently exposes sensitive positional information. To address this gap and achieve a better balance between efficiency and privacy, we propose CipherSkip, an efficient FHE-compatible SpGEMM framework that enables oblivious data and position processing under a Single Instruction Multiple Data (SIMD) scheme. Moreover, we extend our method to support an arbitrary number of sparse matrices (FHE-SpGEMCM). The efficiency analysis shows that our method achieves an average homomorphic computation cost of (nAnB)2/n2N, where nA and nB represent the number of nonzero elements in A and B respectively, n is the shared inner dimension of the multiplication, and N denotes the batch size used in FHE. Experimental results demonstrate that for square matrices of scale 29, our scheme achieves an average speedup of 439.25 × and a 10.68 × reduction in memory consumption compared to state-of-the-art baselines that ignore sparsity. Furthermore, when the scale increases to 213, our method yields up to a 1201.77 × speedup over baselines that only exploit the sparsity of a single matrix.

Due to the power of learning representations from unlabeled graphs, graph contrastive learning (GCL) has shown excellent performance in community detection tasks. Existing GCL-based methods on the community detection usually focused on learning attribute representations of individual nodes, which, however, ignores structure semantics of communities (e.g., nodes in the same community should be structurally cohesive). Therefore, in this paper, we consider the community detection under the community structure semantics and propose an effective framework for graph contrastive learning under structure semantics (GCLS2) to detect communities. To seamlessly integrate interior dense and exterior sparse characteristics of communities with our contrastive learning strategy, we employ classic community structures to extract high-level structural views and design a structure semantic expression module to augment the original structural feature representation. Moreover, we formulate the structure contrastive loss to optimize the feature representation of nodes, which can better capture the topology of communities. To adapt to large-scale networks, we design a high-level graph partitioning (HGP) algorithm that minimizes the community detection loss for GCLS2 online training. It is worth noting that we prove a lower bound on the training of GCLS2 from the perspective of the information theory, explaining why GCLS2 can learn a more accurate representation of the structure. Extensive experiments have been conducted on various real-world graph datasets and confirmed that GCLS2 outperforms nine state-of-the-art methods, in terms of the accuracy, modularity, and efficiency of detecting communities.

Due to the absence or mismatch of semantic information, existing few-shot image generation methods suffer from unsatisfactory generation quality and diversity, which have minimal benefits as data augmentation for downstream classification tasks. Reformatting the contextual and textural information of features at different scales, we propose a novel Feature Equalization Fusion Generative Adversarial Network (EqGAN) for few-shot image generation. Specifically, we first decompose the encoded features into textual and structural components to mitigate the influence of irrelevant and redundant information. Based on feature correlation learning and attention mechanism, we then obtain fused features by refining different contents (i.e., textures and structures) with a more fine-grained semantic alignment. Moreover, an attention-based reconstruction loss and a consistency-based equalization loss are devised to provide better training stability and generation performance. Comprehensive experiments on three public datasets demonstrate that EqGAN not only significantly improves the FID scores (by up to 14.10%) and LPIPS scores (by up to 3.17%) of generated images, but also outperforms the state-of-the-art in terms of accuracy (by up to 3.89%) for downstream classification.

Due to the semantic entanglement in fusion strategies or unstable training in complicated image transformations, existing few-shot image generation methods still suffer from low generation quality and diversity. To tackle the above problems, we propose a novel fusion- and transformation-based framework named content Fusion with style Transformation Generative Adversarial Network (FiTGAN) for few-shot image generation. The basic assumption is that any image consists of a collection of content-related and style-related features. FiTGAN disentangles internal representations with two independent encoders and combines the fused contents and transformed styles to generate new images. Specifically, we design a multi-scale content fusion strategy and a reparameterized style transformation mechanism to learn more fine-grained semantics without changing category-relevant attributes. Furthermore, we formulate a content reconstruction loss and a style divergence loss to provide better training stability and generation performance. Comprehensive experiments on three well-known datasets demonstrate that FiTGAN can not only produce more realistic and diverse images for few-shot image generation but also achieve better classification accuracy for downstream visual applications with limited data.

Source localization, the inverse problem of information diffusion, shows fundamental importance for understanding social dynamics. While achieving notable progress, existing solutions are typically exposed to the risk of error accumulation, and require a large number of observations for effective inference. However, it is often impractical to obtain quantities of observations in real scenarios, highlighting the need for a transferable model with broad applicability. Recently, Riemannian geometry has demonstrated its effectiveness in information diffusion and offers guidance in knowledge transfer, but has yet to be explored in source localization. In light of the issues above, we propose to study transferable source localization from a fresh geometric perspective, and present a novel approach (Trace) on the Riemannian manifold. Concretely, we establish a structural Schrodinger bridge to directly model the map between source and final distributions, where a functional curvature, encapsulating the graph structure, is formulated to govern the Schrodinger bridge and facilitate domain adaptation. Furthermore, we design a simple yet effective learning algorithm for Riemannian Schrodinger bridges (geodesics bridge matching) in which we prove the optimal projection holds for Riemannian measure so that the expensive iterative procedure is avoided. Extensive experiments demonstrate the effectiveness and transferability of Trace on both synthetic and real datasets.

Although various methods are proposed to generate music accompaniment tracks according to the main music track, they suffer from the problems of modeling music dependencies and representing music data, therefore, generating high-quality music accompaniment remains a challenging task.To address this issue, we propose a multi-track sequential convolutional neural network (MuseCNN) to generate accompaniment tracks corresponding to the main music track.Inspired by the similarity between pianoroll representation and pictures, we transform the pianoroll data into a two-channel music representation matrix and feed it into the convolutional neural network (CNN).Using a hierarchical loss function, we integrate all music tracks to maintain the coherence and harmony of the music.Based on the three-level loss design and multiple CNNs, the problem of modeling music dependencies can be solved.The experimental results indicate that our multi-CNN model can effectively learn complex music dependencies and generate harmonious longsequence polyphonic music.

In many real-world applications such as social network analysis, knowledge graph discovery, biological network analytics, and so on, graph data management has become increasingly important and has drawn much attention from the database community. While many graphs (e.g., Twitter, Wikipedia, etc.) are usually evolving over time, it is of great importance to study the continuous subgraph matching (CSM) problem, a fundamental, yet challenging, graph operator, which continuously monitors subgraph matching results over dynamic graphs with a stream of edge updates. To efficiently tackle the CSM problem, we carefully design a general CSM processing framework, based on novel DynamIc Vertex DomINance Embedding (DIVINE), which maps vertex neighborhoods into an embedding space to enable efficient subgraph matching and incremental maintenance under dynamic updates. Inspired by low pruning power for high-degree vertices, we propose a new degree grouping technique to decompose high-degree star patterns into groups of lower-degree star substructures, and devise degree-aware star substructure synopses (DAS 3 ) over embeddings of star substructure groups. We develop efficient algorithms to incrementally maintain dynamic graphs and answer CSM queries by traversing DAS 3 synopses and applying our designed vertex dominance and range pruning strategies. Through extensive experiments, we confirm the efficiency of our proposed DIVINE approach over both real and synthetic graphs.

For the past decades, the subgraph similarity search over a large-scale data graph has become increasingly important and crucial in many real-world applications, such as social network analysis, bioinformatics network analytics, knowledge graph discovery, and many others. While previous works on subgraph similarity search used various graph similarity metrics such as the graph isomorphism, graph edit distance, and so on, in this paper, we propose a novel problem, namely subgraph similarity search under aggregated neighbor difference semantics (S 3 AND), which identifies subgraphs g in a data graph G that are similar to a given query graph q by considering both keywords and graph structures (under new keyword/structural matching semantics). To efficiently tackle the S 3 AND problem, we design two effective pruning methods, keyword set and aggregated neighbor difference lower bound pruning , which rule out false alarms of candidate vertices/subgraphs to reduce the S 3 AND search space. Furthermore, we construct an effective indexing mechanism to facilitate our proposed efficient S 3 AND query answering algorithm. Through extensive experiments, we demonstrate the effectiveness and efficiency of our S 3 AND approach over both real and synthetic graphs under various parameter settings.

Function offloading problems play a crucial role in optimizing the performance of applications in serverless edge computing (SEC). Existing research has extensively explored function offloading strategies based on optimizing a single objective. However, a significant challenge arises when users expect to optimize multiple objectives according to the relative importance of these objectives. This challenge becomes particularly pronounced when the relative importance of the objectives dynamically shifts. Consequently, there is an urgent need for research into multi-objective function offloading methods. In this paper, we redefine the SEC function offloading problem as a dynamic multi-objective optimization issue and propose a novel approach based on Multi-objective Reinforcement Learning (MORL) called MOSEC. MOSEC can coordinately optimize three objectives, i.e., application completion time, User Device (UD) energy consumption, and user cost. To reduce the impact of extrapolation errors, MOSEC integrates a Near-on Experience Replay (NER) strategy during the model training. Furthermore, MOSEC adopts our proposed Earliest First (EF) scheme to maintain the policies learned previously, which can efficiently mitigate the catastrophic policy forgetting problem. Extensive experiments conducted on various generated applications demonstrate the superiority of MOSEC over state-of-the-art multi-objective optimization algorithms.

Learning to collaborate has witnessed significant progress in multi-agent reinforcement learning (MARL). However, promoting coordination among agents and enhancing exploration capabilities remain challenges. In multi-agent environments, interactions between agents are limited in specific situations. Effective collaboration between agents thus requires a nuanced understanding of when and how agents' actions influence others.To this end, in this paper, we propose a novel MARL algorithm named Situation-Dependent Causal Influence-Based Cooperative Multi-agent Reinforcement Learning (SCIC), which incorporates a novel Intrinsic reward mechanism based on a new cooperation criterion measured by situation-dependent causal influence among agents.Our approach aims to detect inter-agent causal influences in specific situations based on the criterion using causal intervention and conditional mutual information. This effectively assists agents in exploring states that can positively impact other agents, thus promoting cooperation between agents.The resulting update links coordinated exploration and intrinsic reward distribution, which enhance overall collaboration and performance.Experimental results on various MARL benchmarks demonstrate the superiority of our method compared to state-of-the-art approaches.

The Israeli-Palestinian conflict is complex and longstanding. This study uses textual analysis through the lens of moral foundations theory to explore how moral values, emotional expressions, and political ideologies are reflected in tweets about the Israeli-Palestine Conflict. By analyzing public discourse and social media interactions, the study seeks to uncover the underlying moral frameworks and emotional responses that shape public perspectives on this ongoing conflict. The results reveal three key findings: 1) both anti-Israel and anti-Hamas tweets emphasize conflict, war, and human rights concerns, characterized by strong negative emotions; 2) anti-Hamas tweets exhibit higher emotional intensity, particularly around specific violent incidents and key figures; and 3) anti-Israel tweets encompass a broader range of issues, such as campus protests and anti-Semitism, with a focus on Israel’s policies and actions from a moral and human rights perspective. This study combines emotion and moral framework analysis, which is rarely used for war related discourse. By combining these perspectives, the research provides valuable theoretical and practical insights that deepen our understanding of how moral and emotional factors shape public opinion on the Israeli-Palestinian conflict.

Few-shot image generation, as an important yet challenging visual task, still suffers from the trade-off between generation quality and diversity. According to the principle of feature-matching learning, existing fusion-based methods usually fuse different features by using similarity measurements or attention mechanisms, which may match features inaccurately and lead to artifacts in the texture and structure of generated images. In this paper, we propose an exact Fusion via Feature Distribution matching Generative Adversarial Network (F2DGAN) for few-shot image generation. The rationale behind this is that feature distribution matching is much more reliable than feature matching to explore the statistical characters in image feature space for limited real-world data. To model feature distributions from only a few examples for feature fusion, we design a novel variational feature distribution matching fusion module to perform exact fusion by empirical cumulative distribution functions. Specifically, we employ a variational autoencoder to transform deep image features into distributions and fuse different features exactly by applying histogram matching. Additionally, we formulate two effective losses to guide the matching process for better fitting our fusion strategy. Extensive experiments compared with state-of-the-art methods on three public datasets demonstrate the superiority of F2DGAN for few-shot image generation in terms of generation quality and diversity, and the effectiveness of data augmentation in downstream classification tasks11Code is available at: https:/github.com/ZYBOBO/F2DGAN.

In many real-world applications such as social network analysis and online marketing/advertising, community detection is a fundamental task to identify communities (subgraphs) in social networks with high structural cohesiveness. While previous works focus on detecting communities alone, they do not consider the collective influences of users in these communities on other user nodes in social networks. Inspired by this, in this paper, we investigate the influence propagation from some seed communities and their influential effects that result in the influenced communities. We propose a novel problem, named Top-L most Influential Community DEtection ($\text{Top}L$-ICDE) over social networks, which aims to retrieve top-$L$seed communities with the highest influences, having high structural cohesiveness, and containing user-specified query keywords. To efficiently tackle the$\text{Top}L$-ICDE problem, we design effective pruning strategies to filter out false alarms of seed communities and propose an effective index mechanism to facilitate efficient Top-$L$community retrieval. We develop an efficient$\text{Top}L$-ICDE answering algorithm by traversing the index and applying our proposed pruning strategies. We also formulate and tackle a variant of$\text{Top}L$-ICDE, named diversified top-L most influential community detection ($\text{Top}L$-ICDE), which returns a set of$L$diversified communities with the highest diversity score (i.e., collaborative influences by$L$communities). We prove that$\text{DTop}L$-ICDE is NP-hard, and propose an efficient greedy algorithm with our designed diversity score pruning. Through extensive experiments, we verify the efficiency and effectiveness of our proposed$\text{Top}L$-ICDE and$\text{DTop}L$-ICDE approaches over real/synthetic social networks under various parameter settings.

The classic problem of exact subgraph matching returns those subgraphs in a large-scale data graph that are isomorphic to a given query graph, which has gained increasing importance in many real-world applications such as social network analysis, knowledge graph discovery in the Semantic Web, bibliographical network mining, and so on. In this paper, we propose a novel and effective graph neural network (GNN)-based path embedding framework (GNN-PE), which allows efficient exact subgraph matching without introducing false dismissals. Unlike traditional GNN-based graph embeddings that only produce approximate subgraph matching results, in this paper, we carefully devise GNN-based embeddings for paths, such that: if two paths (and 1-hop neighbors of vertices on them) have the subgraph relationship, their corresponding GNN-based embedding vectors will strictly follow the dominance relationship. With such a newly designed property of path dominance embeddings, we are able to propose effective pruning strategies based on path label/dominance embeddings and guarantee no false dismissals for subgraph matching. We build multidimensional indexes over path embedding vectors, and develop an efficient subgraph matching algorithm by traversing indexes over graph partitions in parallel and applying our pruning methods. We also propose a cost-model-based query plan that obtains query paths from the query graph with low query cost. Through extensive experiments, we confirm the efficiency and effectiveness of our proposed GNN-PE approach for exact subgraph matching on both real and synthetic graph data.

Mobile smart devices provide convenience for people’s daily life with the users’ data, but also put consumers’ privacy and security at risk. Privacy-enhancing technologies (PETs), including secure two/multi-party computation, have emerged as solutions to alleviate privacy concerns in mobile cloud computing (MCC). However, cloud servers, although capable of easing the burden of PETs, introduce potential risks by being malicious and colluding with computation parties to access additional private data. In this article, we propose a privacy-preserving cloud-assisted two-party computation scheme and the optimized variant with the half-gate method in MCC with a higher security level. To the best of our knowledge, the work is the first cloud-assisted two-party computation, designed to resist all collusion attacks in the malicious model. This is achieved by distributing circuit generation tasks among the parties and separately processing private inputs based on authenticated garbled circuits. Security analysis demonstrates that our scheme ensures correctness and fairness. Performance comparison results indicate the efficiency of our work, even with stronger security against malicious servers and any collusion attack. It outperforms the state-of-the-art scheme, particularly in terms of the server’s communication cost in the online phase, achieving a remarkable reduction of approximately 96.8%.

Due to their fast speed and easy deployment, Unmanned Aerial Vehicles (UAVs) have been widely used across various sectors, such as earthquake rescue, medical assistance, and smart agriculture. However, UAVs in delivery networks face significant challenges due to limited battery life and computational capabilities, particularly for tasks that entail intensive computing workflows. In this context, Multi-access Edge Computing (MEC), which provides computing resources in close proximity to mobile terminal devices, has emerged as a promising solution. UAVs can offload computing tasks to MEC resources across diverse Internet of Things (IoT) environments. Although task offloading can enhance their task processing capability, it simultaneously brings additional costs, encompassing data transmission time and energy consumption. To address these issues, this paper proposes a novel workflow scheduling method based on the Proximal Policy Optimization (PPO) algorithm, aimed at optimizing UAV energy consumption within MEC environments. The proposed approach establishes a learning-based workflow scheduling strategy harnessing the adaptability of the PPO algorithm to manage dynamic and intricate scenarios, which facilitates efficient task allocation to optimal computational resources while accounting for flight time constraints. Extensive experiments conducted on various well-known scientific workflow benchmarks in real-world UAV delivery networks validate the effectiveness of our method. Compared with state-of-the-art methods, our approach significantly reduces UAV energy consumption and task completion time, simultaneously increasing UAV’s effective payload capacity.

Due to repetitive trial-and-error style interactions between agents and a fixed traffic environment during the policy learning, existing Reinforcement Learning (RL)-based Traffic Signal Control (TSC) methods greatly suffer from long RL training time and poor adaptability of RL agents to other complex traffic environments. To address these problems, we propose a novel Adversarial Inverse Reinforcement Learning (AIRL)-based pre-training method named InitLight, which enables effective initial model generation for TSC agents. Unlike traditional RL-based TSC approaches that train a large number of agents simultaneously for a specific multi-intersection environment, InitLight pre-trains only one single initial model based on multiple single-intersection environments together with their expert trajectories. Since the reward function learned by InitLight can recover ground-truth TSC rewards for different intersections at optimality, the pre-trained agent can be deployed at intersections of any traffic environments as initial models to accelerate subsequent overall global RL training. Comprehensive experimental results show that, the initial model generated by InitLight can not only significantly accelerate the convergence with much fewer episodes, but also own superior generalization ability to accommodate various kinds of complex traffic environments.

Although Reinforcement Learning (RL)-based methods have been widely researched in Traffic Signal Control (TSC), they still suffer from the problems of poor adaptation to real-world traffic scenarios and slow convergence to optimized solutions. This is because RL-based TSC methods have a high dependency on accurate modeling of the environment. With transportation infrastructure constraints, some vehicle dynamic information in the road network is difficult to obtain in real-time, which strongly limits the capability of RL agents. To address this problem, we propose a novel real-time federated traffic signal control system named RTLight, which can efficiently control traffic lights in real-time for multi-intersection scenarios. Based on the digital twin, the RL agent can obtain sufficient traffic information and interact with the environment in real time. Inspired by federated learning, our system supports knowledge sharing among intersections, which improves the overall convergence rate and control performance. Note that, we have deployed our RTLight system for large-scale application validation in Xishan district, Wuxi, China. Experimental results obtained from various real-world traffic scenarios demonstrate that RTLight can significantly improve the control performance.

Although reinforcement learning (RL) approaches are promising in autonomous traffic signal control (TSC), they often suffer from the unfairness problem that causes extremely long waiting time at intersections for partial vehicles. This is mainly because the traditional RL methods focus on optimizing the overall traffic performance, while the fairness of individual vehicles is neglected. To address this problem, we propose a novel RL-based method named FairLight for the fair and efficient control of traffic with variable phase duration. Inspired by the concept of user satisfaction index (USI) proposed in the transportation field, we introduce a fairness index in the design of key RL elements, which specially considers the travel quality (e.g., fairness). Based on our proposed hierarchical action space method, FairLight can accurately allocate the duration of traffic lights for selected phases. Experimental results obtained from various well-known traffic benchmarks show that, compared with the state-of-the-art RL-based TSC methods, FairLight can not only achieve better fairness performance but also improve the control quality from the perspectives of the average travel time of vehicles and RL convergence speed.

Although Reinforcement Learning (RL) has been successfully applied in traffic control, it suffers from the problems of high average vehicle travel time and slow convergence to optimized solutions. This is because, due to the scalability restriction, most existing RL-based methods focus on the optimization of individual intersections while the impact of their cooperation is neglected. Without taking all the correlated intersections as a whole into account, it is difficult to achieve global optimization goals for complex traffic scenarios. To address this issue, this paper proposes a novel federated reinforcement learning approach named FedLight to enable optimal signal control policy generation for multi-intersection traffic scenarios. Inspired by federated learning, our approach supports knowledge sharing among RL agents, whose models are trained using decentralized traffic data at intersections. Based on such model-level collaborations, both the overall convergence rate and control quality can be significantly improved. Comprehensive experimental results demonstrate that compared with the state-of-the-art techniques, our approach can not only achieve better average vehicle travel time for various multi-intersection configurations, but also converge to optimal solutions much faster.