The isomorphism problem is a key challenge in both graph and hypergraph domains, crucial for applications like protein design, chemical pathways, and community detection. Hypergraph isomorphism, which models high-order relationships in real-world scenarios, remains underexplored compared to the graph isomorphism. Current algorithms for hypergraphs, like the 1-dimensional generalized Weisfeiler-Lehman test (1-GWL), lag behind advancements in graph isomorphism tests, limiting most hypergraph neural networks to 1-GWL's expressive power. To address this, we propose the high-dimensional GWL (k-GWL), generalizing k-WL from graphs to hypergraphs. We prove that k-GWL reduces to k-WL for simple graphs, and thus develop a unified isomorphism method for both graphs and hypergraphs. We also successfully establish a clear and complete understanding of the GWL hierarchy of expressivity, showing that (k+1)-GWL is more expressive than k-GWL with illustrative examples. Based on k-GWL, we develop a hypergraph neural network model named k-HNN with improved expressive power of k-GWL, which achieves superior performance on real-world datasets, including a 6\% accuracy improvement on the Steam-Player dataset over the runner-up. Our code is available at https://github.com/talence-zcq/KGWL.

During somatic cell nuclear transfer (SCNT), precise removal of the oocyte genetic material is critical. However, due to the invisibility of the genetic material (spindle) under brightfield observation and the potential displacement caused by the movement of micropipettes, accurately positioning the micropipette at the spindle poses a significant challenge. This study introduces an approach for optimal spindle removal by predicting its position. Initially, the polarization imaging system visualized the oocyte spindle, while a Multi-Feature Adaptive Kernel Correlation Filter (MFAKCF) algorithm tracked the spindle with 92.84% accuracy. Subsequently, enhancements were made to the Nonlinear Mass-Spring-Damper (NMSD) model to simulate live oocyte mechanical characteristics. Adjustments to NMSD model parameters simulated spindle displacement variations under diverse experimental conditions. Finally, the optimal spindle removal position was determined using NMSD model to simulate the micropipette approach to the spindle and the resulting position of spindle displacement. Experimental validation showed that the predictive accuracy of this model was 97.26%, with an average positional error of$0.4~\mu $m. Using this approach method can reduce cytoplasm loss to 4.5% and have a 100% enucleation success rate. Thus, the proposed prediction based optimal spindle removal position method can effectively anticipates spindle final positions, aiding in minimizing cytoplasmic loss during spindle removal. Note to Practitioners—Accurate oocyte nucleus removal is crucial for somatic cell nuclear transfer (SCNT) but challenging due to spindle invisibility under brightfield microscopy and displacement caused by micropipette movements. This study proposes a predictive method to address these issues. The polarization imaging system was used to visualize the spindle, and a MFAKCF tracking algorithm enabled real-time tracking. An enhanced NMSD model simulated spindle displacement, enabling accurate position prediction and reducing cytoplasmic loss during removal. This method offers a reliable tool for precise spindle removal in SCNT and broader applications in biomedical micromanipulation.

Most of existing path finding problems focused on searching a path with the minimum cost, such as shortest-path length and shortest travel time. In this paper, we consider a new path finding problem, i.e., length-constrained maximum density path (LDP) problem. Given a graph with length and weight on each edge, the LDP problem aims to find the maximum density path between two nodes under a specified length constraint, where the density of the path is defined as the ratio of the path weight to the path length. To the best of our knowledge, there are no existing works that focus on this problem. We prove the problem is NP-hard. Then we propose an A*-based exact algorithm to acquire the optimal solution. Due to the expensive computational overhead of the A*-based exact algorithm, we further propose two effective approximation algorithms, i.e., the label setting algorithm and the top-k based network expansion (k-NE) algorithm. Extensive experiments on four real and synthetic datasets verify the efficiency and effectiveness of the proposed algorithms.

Temporal Knowledge Graph (TKG) reasoning, aiming to predict future unknown facts based on historical information, has attracted considerable attention due to its great practical value.Insight into history is the key to predict the future.However, most existing TKG reasoning models singly capture repetitive history, ignoring the entity's multi-hop neighbour history which can provide valuable background knowledge for TKG reasoning.In this paper, we propose Multi-Granularity History and Entity Similarity Learning (MGESL) model for Temporal Knowledge Graph Reasoning, which models historical information from both coarse-grained and fine-grained history.Since similar entities tend to exhibit similar behavioural patterns, we also design a hypergraph convolution aggregator to capture the similarity between entities.Furthermore, we introduce a more realistic setting for the TKG reasoning, where candidate entities are already known at the timestamp to be predicted.Extensive experiments on three benchmark datasets demonstrate the effectiveness of our proposed model.

Accurate and real-time traffic state prediction is of great practical importance for urban traffic control and web mapping services. With the support of massive data, deep learning methods have shown their powerful capability in capturing the complex spatial-temporal patterns of traffic networks. However, existing approaches use pre-defined graphs and a simple set of spatial-temporal components, making it difficult to model multi-scale spatial-temporal dependencies. In this paper, we propose a novel dynamic graph convolution network with attention fusion to tackle this gap. The method first enhances the interaction of temporal feature dimensions, and then it combines a dynamic graph learner with GRU to jointly model synchronous spatial-temporal correlations. We also incorporate spatial-temporal attention modules to effectively capture long-range, multifaceted domain spatial-temporal patterns. We conduct extensive experiments in four real-world traffic datasets to demonstrate that our method surpasses state-of-the-art performance compared to 18 baseline methods.

In ride-hailing services, drivers need to deliver passengers from sources to destinations over road networks. Since road network topologies for pedestrians are usually different from those for vehicles, and most of traffics only affect vehicles instead of pedestrians, adopting suitable pick-up and drop-off points can avoid detours and heavy traffics, and then reduce the trip travel time for passengers and drivers. However, to the best of our knowledge, there is no existing work about optimal pick-up and drop-off point recommendation in ride-hailing services. In this paper, we initiate the study of this problem. We not only give an exhaustive search algorithm but also devise a much more efficient method based on a delicate virtual graph to find the optimal pick-up and drop-off points for drivers and their passengers. Extensive experiments on two real datasets verify the efficiency and effectiveness of our proposed algorithms.

In this paper, we focus on a new route recommendation problem, i.e., when a user gives a keyword and range constraint, the route that contains the maximum number of POIs tagged with the keyword or similar POIs in the range will be returned for him. This is a practical problem when people want to explore a place, e.g., find a route within 2 km containing as many clothing stores as possible. To solve the problem, we first calculate the score of each edge in road networks based on the number and similarity of POIs. Then, we reformulate the problem into finding the path in a graph with the maximum score within the distance constraint problem, which is proved NP-hard. Given this, we not only propose an exact branch and bound (BnB) algorithm, but also devise a more efficient top-k based network expansion (k-NE) algorithm to find the near-optimal solution. Extensive experiments on real datasets not only verify the effectiveness of the proposed route recommendation algorithm, but also show that the efficiency and accuracy of k-NE algorithm are completely acceptable.

The continuing development of intelligent transportation terminals and the massive generated traffic data have placed tremendous pressure on traffic data acquisition. However, most of existing intelligent transportation systems and applications rely on well-defined data, while few studies focus on how to collect live traffic data from various vehicle terminals in a large number. To solve this problem, we propose an efficient and non-blocking data acquisition system in this paper, which can retrieve traffic data based on different priority or QoS requirements from a large number of various terminals in real-time, so that the application layer can easily access certain type of traffic data it needs. Extensive experiment and simulation results prove the efficiency, reliability, and scalability of our proposed system. Besides, two real applications based on the proposed system are introduced in the paper.

Shortest path queries on road networks are widely used in location-based services (LBS), e.g., finding the shortest route from my home to the airport through Google Maps. However, when there are a large number of path queries arrived concurrently or in a short while, an LBS provider (e.g., Google Maps) has to endure a high workload and then may lead to a long response time to users. Therefore, path caching services are utilized to accelerate large-scale path query processing, which try to store the historical path results and reuse them to answer the coming queries directly. However, most of existing path caches are organized based on nodes of paths; hence, the underlying road network topology is still needed to answer a path query when its querying origin or destination lies on edges. To overcome this limitation, we propose an edge-based shortest path cache in this paper that can efficiently handle queries without needing any road information, which is much more practical in the real world. We achieve this by designing a totally new edge-based path cache structure, an efficient R-tree-based cache lookup algorithm, and a greedy-based cache construction algorithm. Extensive experiments on a real road network and real point-of-interest datasets are conducted, and the results show the efficiency, scalability, and applicability of our proposed caching techniques.

Although the travel time is the most important information in road networks, many spatial queries, e.g.,$k$-nearest-neighbor ($k$-NN) and range queries, for location-based services (LBS) are only based on the network distance. This is because it is costly for an LBS provider to collect real-time traffic data from vehicles or roadside sensors to compute the travel time between two locations. With the advance of web mapping services, e.g., Google Maps, Microsoft Bing Maps, and MapQuest Maps, there is an invaluable opportunity for using such services for processing spatial queries based on the travel time. In this paper, we propose a server-sideSpatialMashupService (SMS) that enables the LBS provider to efficiently evaluate$k$-NN queries in road networks using the route information and travel time retrieved from an external web mapping service. Due to the high cost of retrieving such external information, the usage limits of web mapping services, and the large number of spatial queries, we optimize the SMS for a large number of$k$-NN queries. We first discuss how the SMS processes a single$k$-NN query using two optimizations, namely,direction sharingandparallel requesting. Then, we extend them to process multiple concurrent$k$-NN queries and design a performance tuning tool to provide a trade-off between the query response time and the number of external requests and more importantly, to prevent a starvation problem in the parallel requesting optimization for concurrent queries. We evaluate the performance of the proposed SMS using MapQuest Maps, a real road network, real and synthetic data sets. Experimental results show the efficiency and scalability of our optimizations designed for the SMS.