Reachability queries are a core operation in graph analytics. Existing labeling methods assume a global query space and construct uniform labels for all vertices. In practice, however, many systems issue queries over semantically structured endpoint domains such as V_s × V_t, where only a subset of vertices serve as meaningful sources or targets. This mismatch makes global labeling redundant and inefficient. We propose Partitioned Tree-Cover Interval Labeling (PTIL), a restricted-domain reachability indexing framework that extends classical Tree-Cover Labeling. PTIL timestamps only target vertices and stores compact disjoint intervals at sources, reducing each query to a single membership test while avoiding unnecessary global labels. By partitioning targets into groups, PTIL provides an explicit and predictable space–time trade-off: finer grouping yields lower latency at the cost of larger index size. PTIL also supports dynamic updates to endpoint domains. We further develop two instantiations: PTIL-g, a grouped scheme for scalable domain-aligned indexing, and PTIL-p, which additionally leverages query distributions for further prioritization when available. Experiments on real and synthetic graphs show that PTIL-g achieves order-of-magnitude lower query latency than state-of-the-art baselines, while PTIL-p provides additional gains under skewed workloads, with near-linear and predictable space–time behavior.

Legal information retrieval demands high precision, yet traditional ''Retrieve-then-Rerank'' pipelines with two separate models suffer from cascading error propagation and knowledge disconnects between stages. To address these issues, we propose RULER, a Robust Unified LLM-based Efficient Retrieval that integrates efficient Bi-Encoder retrieval and high-precision Cross-Encoder reranking within a parameter-sharing architecture. To mitigate the Phantom Hits problem that irrelevant documents are assigned unreasonably high confidence, we introduce a Distribution-Robust Data Construction strategy that explicitly simulates pure-negative candidate groups. This is coupled with a Dynamic Margin Ranking Objective and Maximum Entropy Regularization, which collectively enforce uncertainty on irrelevant samples and enhance robustness. Extensive experiments on the JuDGE and LeCaRDv2 benchmarks demonstrate that RULER achieves state-of-the-art performance, outperforming all independent retrievers in retrieval tasks and surpassing competing unified architectures—where retriever and reranker parameters are shared—in high-precision reranking.

Temporal Betweenness Centrality (TBC) measures how often a node appears on optimal temporal paths, reflecting its importance in temporal networks. However, exact computation is highly expensive, and real-world TBC distributions are extremely imbalanced, causing learning-based models to overfit to zero-centrality nodes and fail to identify truly central nodes. Existing graph neural networks (GNNs) either ignore temporal dependencies or cannot handle such extreme imbalance. To address these issues, we propose CLGNN, a scalable and inductive contrastive learning-based GNN for accurate TBC prediction. CLGNN preserves temporal path validity through an instance graph and encodes structural, path-time aware dependencies via dual aggregation. To mitigate imbalance, a stability-based clustering-guided contrastive module separates nodes of different centrality levels in representation space, while a regression head estimates TBC values. Extensive experiments on diverse benchmarks demonstrate that CLGNN is scalable, generalizable, and effective.

Image classification, a fundamental task in computer vision, often suffers from limited labeled samples, a problem commonly referred to as few-shot learning. Model-Agnostic Meta-Learning (MAML) addresses this issue by learning a set of meta-parameters from a variety of similar tasks, enabling rapid adaptation to new tasks within the same distribution using only a few gradient updates. However, traditional MAML frameworks usually encounter two major limitations: one is that they seek a common initialization shared across the entire task distribution, which restricts their capacity to capture the diversity inherent in varying task distributions. The other is that they resort to conventional optimizers (e.g., SGD), which limits their ability to adaptively learn across different domain tasks. To address these limitations, we propose a Task-adaptive Model-Agnostic MetaLearning (TMAML) framework. TMAML improves the existing MAML framework by jointly learning both the initialization and the parameter update rules, tailored for each individual task. The model first learns the domain information of the task as prior parameters, enabling more efficient and effective adaptation in both the initialization and update stages. During initialization, TMAML comprehensively considers the prior parameters of the specific task as well as the intrinsic information of the current samples. When learning the parameter update rules, it fully incorporates the prior parameters of the specific task along with the model's current learning state to guide adaptation more precisely. Experimental results demonstrate that TMAML effectively improves upon existing methods, boosting image classification performance across a wide range of settings. Notably, compared to the state-of-the-art cross-domain few-shot learning method, TMAML achieves an accuracy improvement of up to 3.56 % on 3-domain 5-way 4-shot tasks and up to 5.41 % on 5-domain 5-way 5-shot tasks.

In recent years, deploying deep learning models on edge devices has become pervasive, driven by the increasing demand for intelligent edge computing solutions across various industries. From industrial automation to intelligent surveillance and healthcare, edge devices are being leveraged for real-time analytics and decision-making. Existing methods face two challenges when deploying machine learning models on edge devices. The first challenge is handling the execution order of operators with a simple strategy, which can lead to a potential waste of memory resources when dealing with directed acyclic graph structure models. The second challenge is that they usually process operators of a model one by one to optimize the inference latency, which may lead to the optimization problem getting trapped in local optima. We present MemoriaNova, comprising BTSearch and GenEFlow, to solve these two problems. BTSearch is a graph state backtracking algorithm with efficient pruning and hashing strategies designed to minimize memory overhead during inference and enlarge latency optimization search space. GenEFlow, based on genetic algorithms (GA), integrates latency modeling, and memory constraints to optimize distributed inference latency. This innovative approach considers a comprehensive search space for model partitioning, ensuring robust and adaptable solutions. We implement BTSearch and GenEFlow and test them on 11 deep-learning models with different structures and scales. The results show that BTSearch can reach 12% memory optimization compared with the widely used random execution strategy. At the same time, GenEFlow reduces inference latency by 33.9% in distributed systems with four-edge devices.

Numerous real-world networks are represented as temporal graphs, which capture the dynamics of connections over time. Identifying important nodes on temporal graphs has a plethora of real-life applications, such as information propagation and influential user identification, etc. Temporal Katz centrality, a popular temporal metric, gauges the importance of nodes by taking into account both the number of temporal walks and the timespan between the interactions. The computation of traditional temporal Katz centrality is computationally expensive, especially when applied to massive temporal graphs. Therefore, in this paper, we design a temporal graph neural network to approximate temporal Katz centrality computation. To the best of our knowledge, we are the first to address temporal Katz centrality computation purely from a learning-based perspective. We propose a time-injected self-attention model that consists of two phases. In the first phase, we utilize a time-injected self-attention mechanism to acquire node representations that encompass both structural information and temporal relevance. The second phase is structured as a multi-layer perceptron (MLP) which uses the learned node representation to predict node rankings. Furthermore, normalization and neighbor sampling strategies are integrated into the model to enhance its overall performance. Extensive experiments on real-world networks demonstrate the efficiency and accuracy of TATKC.

Betweenness centrality of a vertex in a graph evaluates how often the vertex occurs in the shortest paths. It is a widely used metric of vertex importance in graph analytics. While betweenness centrality on static graphs has been extensively investigated, many real-world graphs are time-varying and modeled as temporal graphs. Examples include social networks and telecommunication networks, where a relationship between two vertices occurs at a specific time. Hence, in this paper, we target efficient methods for temporal betweenness centrality computation. We firstly propose an exact algorithm with the new notion of time instance graph, based on which, we derive a temporal dependency accumulation theory for iterative computation. To reduce the size of the time instance graph and improve the efficiency, we propose an additional optimization, which compresses the time instance graph with equivalent vertices and edges, and extends the dependency theory to the compressed graph. Since it is theoretically complex to compute temporal betweenness centrality, we further devise a probabilistically guaranteed approximate method to handle massive temporal graphs. Extensive experimental results on real-world temporal networks demonstrate the superior performance of the proposed methods. In particular, our exact and approximate methods outperform the state-of-the-art methods by up to two and five orders of magnitude, respectively.

Sequential recommendations are designed to capture user preferences based on their past actions and predict the items they may interact with in the next moment. Benefiting from the self-attention mechanism, methods that utilize side information (such as item categories or brand) to improve the prediction performance of sequential recommendation have yielded promising results. Previous approaches typically directly fuses side information embeddings into item embeddings as inputs to the model. However, this fusion approach overlooks the distinctions in various types of information in sequential pattern inference, and also failing to fully model the relationship between items and side information. In this work, we propose a Dual-Path Side Information Fusion method (DPIF) to better utilize side information for improved recommendation performance. Our model employs two parallel paths for side information fusion modeling. One path obtains the relationship representation within the items and the side information, and the other path obtains the relationship representation between the items and the side information. Subsequently, an attention-based adaptive fusion module is utilized to combine inter-attribute relationship and intra-attribute relationship representation, generating the final user preferences. Extensive experiments were conducted on four real-world datasets, demonstrating the effectiveness of the introduced model. Our source code is available at https://github.com/ZhangYu-x/DPIF.

Bipartite graphs characterize relationships between two different sets of entities, like actor-movie, user-item, and author-paper. The butterfly, a 4-vertices 4-edges (2,2)-biclique, is the simplest cohesive motif in a bipartite graph and is the fundamental component of higher-order substructures. Counting and enumerating the butterflies offer significant benefits across various applications, including fraud detection, graph embedding, and community search. While the corresponding motif, the triangle, in the unipartite graphs has been widely studied in both static and temporal settings, the extension of butterfly to temporal bipartite graphs remains unexplored. In this paper, we investigate the temporal butterfly counting and enumeration problem: count and enumerate the butterflies whose edges establish following a certain order within a given duration. Towards efficient computation, we devise a non-trivial baseline rooted in the state-of-the-art butterfly counting algorithm on static graphs, further, explore the intrinsic property of the temporal butterfly, and develop a new optimization framework with a compact data structure and effective priority strategy. The time complexity is proved to be significantly reduced without compromising on space efficiency. In addition, we generalize our algorithms to practical streaming settings and multi-core computing architectures. Our extensive experiments on 11 large-scale real-world datasets demonstrate the efficiency and scalability of our solutions.

With the development of the smart Internet of Things (IoT), an increasing number of tasks are deployed on the edge of the network. Considering the substantially limited processing capability of IoT devices, task scheduling as an effective solution offers low latency and flexible computation to improve the system performance and increase the quality of services. However, limited computing resources make it challenging to assign the right tasks to the right devices at the edge of the network. To this end, we propose a polynomial-time solution, which consists of three steps, i.e., identifying available devices, estimating device quantity, and searching for feasible schedules. In order to shrink the number of potential schedules, we present a pairwise-allocated strategy (PA). Based on these, a capability average matrix (CAM)-based index is designed to further boost efficiency. In addition, we evaluate the schedules by the technique for order preference by similarity to an ideal solution (TOPSIS). Extensive experimental evaluation using both real and synthetic datasets demonstrates the efficiency and effectiveness of our proposed approach.

Graph pattern matching has been extensively investigated on general graphs without time information over decades. Nevertheless, few studies focus on temporal graphs, where a relationship between two vertices takes place at a specific moment and lingers for some time. In this paper, we propose a new notion so-calledtime-respecting flow graph, in which all paths are time-respecting (i.e., a sequence of contacts with non-decreasing time), and one vertex is distinguished as the root, from which other vertices can be reached via a time-respecting path. Based on this, we explore the problem oftime-respecting flow graph pattern matching on temporal graphs. This problem motivates important applications in epidemiology, information diffusion, crime detection, etc. To address it, we present one baseline algorithm as well as two optimized algorithms that utilize several efficient matching strategies and topological sort based technique to boost efficiency. Extensive experimental evaluation using both real and synthetic data sets demonstrates the effectiveness and efficiency of our proposed algorithms. Compared with baseline method, our optimized algorithms could achieve up to three orders of magnitude speedup.

In this paper, we present an approach to semantic cage generating and semantic cage based finite element mesh editing to allow users to conduct the required editing on complex finite element mesh effectively and efficiently through cage-based deformation during product design. In the approach, design semantics involved in a finite element mesh are incorporated with its cage to enable the cage based and semantic based editing of the finite element mesh. Firstly, the design semantics including semantic features and semantic relations are extracted from the original mesh, and a simplified mesh with the semantics preserved is constructed. Then, the semantic cage without cage-model intersection is automatically created by offsetting the simplified mesh and mapping the semantics from the original mesh to the cage. Finally, the editing manipulation is directly imposed on the semantic features rather than single vertex or face of the cage to achieve the required modification on the mesh. The experimental results show the effectiveness and potentials of the proposed approach.

Volumetric mesh models are widely used nowadays in areas like product quality evaluation, physically-based deformation, numerical simulation, and so on. In the application of Computer Aided Design (CAD) and Computer Aided Engineering (CAE) integration, providing a method to directly manipulate mesh models can reduce much effort in the simulation process. However, this integration is limited or only provided from CAD to CAE at current time. In this paper, we propose a framework for volumetric mesh editing based on feature dimensions. In our framework, the volumetric mesh is first decomposed into volumetric features based on corresponding surface features. Then, random-walk based interpolation algorithm is applied to manipulation of local features. Our framework allows users to change the dimensions of the recognized features on the volumetric mesh directly. Then optimization, which is limited to local features, is employed to refine the tetrahedrons of the volumetric features once the quality of the elements does not meet the requirements. Experimental results show that the features hold precisely after the editing operations. Additionally, the quality of the elements keeps well after the tetrahedral mesh has been edited.