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.

The exponential growth of user-generated comment data on social media platforms has greatly promoted research on text sentiment analysis. However, the presence of conflicting sentiments within user comments, known as 'user comments with noisy labels', poses a significant challenge to the reliability of sentiment analysis models. Many current approaches address this issue by either discarding noisy samples or assigning small weights to them during training, but these strategies can lead to sample wastage and reduced model robustness. In this paper, we present SLaNT, a novel semi-supervised label noise-tolerant framework specifically designed for text sentiment analysis. SLaNT employs a four-module pipeline that includes Noisy Data Identification, Data Augmentation, Noisy Data Relabeling, and Re-training. Notably, SLaNT introduces an early stopping strategy to efficiently identify noisy samples. Additionally, to mitigate confirmation bias during the relabeling of noisy data, a unique co-relabeling strategy based on ensemble learning is integrated into SLaNT. Experimental results on four text user comment datasets demonstrate that SLaNT significantly outperforms four selected strong baselines.

Text clustering has become an important branch in unsupervised learning methods and has been widely used in social media. Recently, Large Language Models (LLMs) represent a significant advancement in the field of AI. Therefore, some works have been dedicated to improving the clustering performance of embedding models with feedback from LLMs. However, current approaches hardly take into consideration the cluster label information between text instances when fine-tuning embedding models, leading to the problem of cluster collision. To tackle this issue, this paper proposes TeC, a novel method operating through teaching and correcting phases. In these phases, LLMs take on the role of teachers, guiding embedding models as students to enhance their clustering performance. The teaching phase imparts guidance on cluster label information to embedding models by querying LLMs in a batch-wise manner and utilizes a proposed weakly-supervised contrastive learning loss to fine-tune embedding models based on the provided cluster label information. Subsequently, the correcting phase refines clustering outcomes obtained by the teaching phase by instructing LLMs to correct cluster assignments of low-confidence samples. The extensive experimental evaluation of six text datasets across three different clustering tasks shows the superior performance of our proposed method over existing state-of-the-art approaches.

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.

Delivery stations play important roles in logistics systems. Well-designed delivery station planning can improve delivery efficiency significantly. However, existing delivery station locations are decided by experts, which requires much preliminary research and data collection work. It is not only time consuming but also expensive for logistics companies. Therefore, in this article, we propose a data-driven pipeline that can transfer expert knowledge among cities and automatically allocate delivery stations. Based on existing well-designed station location planning in the source city, we first train a model to learn the expert knowledge about delivery range selection for each station. Then we transfer the learned knowledge to a new city and design three strategies to select delivery stations for the new city. Due to the differences in characteristics among different cities, we adopt a transfer learning method to eliminate the domain difference so that the model can be adapted to a new city well. Finally, we conduct extensive experiments based on real-world datasets and find the proposed method can solve the problem well.

To improve the classification performance of support vector machines (SVMs) on imbalanced datasets, cost-sensitive learning methods have been proposed, e.g., Different Error Costs (DEC) and Fuzzy SVM for Class Imbalance Learning (FSVM-CIL). They relocate the hyperplane by adjusting the costs associated with misclassifying samples. However, the error costs are determined either empirically or by performing an exhaustive search in the parameter space. Both strategies can not guarantee effectiveness and efficiency simultaneously. In this paper, we proposeATEC, a solution that can efficiently find a preferable hyperplane by automatically tuning the error cost for between-class samples.ATECdistinguishes itself from all existing parameter tuning strategies by two main features: (1) it can evaluate how effective an error cost is in terms of classification accuracy; and (2) it changes the error cost in the right direction if it is not effective. Extensive experiments show that compared with the state-of-art methods, SVMs that are equipped withATECcan not only obtain comparable improvements in terms of F1 score of minority class, area under the precision-recall curve (AUC-PR) and area under the ROC curve (AUC-ROC) scores, but also outperform the grid-search parameter tuning strategy by two orders of magnitude in terms of the training time when a high F1 score is required.

In order to solve the poor performance problem of massive rules reasoning, as well as the inconsistency problem of working memory in distributed rule matching, this article presents the formal definition of interference relations between rules, and proposes a novel approach to distributed rule matching and multiple firing based on MapReduce. This approach adopts the way of access request control to detect and exclude interference rules, then selects several rule instantiations to perform multiple firing and concurrent execution, thus reducing the number of inference cycles effectively. By detecting the interferences between rules, this method selects and executes compatible rule sets, and avoids the inconsistency problem of system working memory. In order to verify the validity of the authors' approach, this article developes a production system based on MapReduce, and applied this approach in the master server of a distributed production system. The experimental results show that their method can promote the performance of massive rules reasoning effectively.

Nowadays, many location-based applications require the ability of querying k-nearest neighbors over a very large scale of moving objects in road networks, e.g., taxi-calling and ride-sharing services. Traditional grid index with equal-sized cells can not adapt to the skewed distribution of moving objects in real scenarios. Thus, to obtain the fast querying response time, the grid needs to be split into more smaller cells which introduces the side-effect of higher memory cost, i.e., maintaining such a large volume of cells requires a much larger memory space at the server side. In this paper, we present SIMkNN, a scalable and in-memory kNN query processing technique. SIMkNN is dual-index driven, where we adopt a R-tree to store the topology of the road network and a hierarchical grid model to manage the moving objects in non-uniform distribution. To answer a kNN query in real time, SIMkNN adopts the strategy that incrementally enlarges the search area for network distance based nearest neighbor evaluation. It is far from trivial to perform the space expansion within the hierarchical grid index. For a given cell, we first define its neighbors in different directions, then propose a cell communication technique which allows each cell in the hierarchical grid index to be aware of its neighbors at anytime. Accordingly, an efficient space expansion algorithm to generate the estimation area is proposed. The experimental evaluation shows that SIMkNN outperforms the baseline algorithm in terms of time and memory efficiency.

In this paper, we propose a new problem: covering the optimal time window over temporal data. Given a duration constraint d and a set of users where each user has multiple time intervals, the goal is to find all time windows which (1) are greater than or equal to the duration d, and (2) can be covered by the intervals from as many as possible users. This problem can be applied to real scenarios where people need to determine the best time for maximizing the number of people to be involved in an activity, e.g., the meeting organization and the online live video broadcasting. As far as we know, there is no existing algorithm that can solve the problem directly. In this paper, we propose two algorithms to solve the problem, the first one is considered as a baseline algorithm called sliding time window (STW), where we utilize the start and end points of all users - intervals to construct time windows satisfying duration d. And then we calculate the number of users whose intervals can cover the current time window. The second method, named TLI, is designed based on the the data structures from the Timeline Index in SAP HANA. In TLI algorithm, we conduct three consecutive phases to achieve the purpose of efficiency improvement, namely construction of Timeline Index, calculation of valid user set and calculation of time windows. Within the third phase, we prune the number of time windows by keeping track of the number of users in current optimal time window, which can help shrink the search space. Through extensive experimental evaluations, we find TLI algorithm outperforms STW two orders of magnitude in terms of querying time.

Recently, many ride sharing systems have been commercially introduced (e.g., Uber, Flinc, and Lyft) forming a multi-billion dollars industry. The main idea is to match people requesting a certain ride to other people who are acting as drivers on their own spare time. The matching algorithm run by these services is very simple and ignores a wide sector of users who can be exploited to maximize the benefits of these services. In this demo, we demonstrate SHAREK; a driver-rider matching algorithm that can be embedded inside existing ride sharing services to enhance the quality of their matching. SHAREK has the potential to boost the performance and widen the user base and applicability of existing ride sharing services. This is mainly because within its matching technique, SHAREK takes into account user preferences in terms of maximum waiting time the rider is willing to have before being picked up as well as the maximum cost that the rider is willing to pay. Then, within its course of execution, SHAREK applies a set of smart filters that enable it to do the matching so efficiently without the need to many expensive shortest path computations.

Due to its significant economic and environmental impact, sharing the ride among a number of drivers (i.e., Car pooling) has recently gained significant interest from industry and academia. Hence, a number of ride sharing services have appeared along with various algorithms on how to match a rider request to a driver who can provide the ride sharing service. However, existing techniques have several limitations that affect the quality of the ride sharing service, and hence hinder its wide applicability. This paper proposes SHAREK, a scalable and efficient ride sharing service that overcomes the limitations of existing approaches. SHAREK allows riders requesting the ride sharing service to indicate the maximum price they are willing to pay for the service and the maximum waiting time before being picked up. In the mean time, SHAREK computes the price of the service based on the distance of the rider trip and the detour that the driver will make to offer the service. Then, SHAREK returns a set of drivers that can make it to the rider within its price and temporal constraints. Since there could be many of such drivers, SHAREK internally prunes those drivers that are dominated by others, i.e., They provide higher price and higher waiting time than other drivers. To realize its efficiency and scalability, SHAREK employs a set of early pruning techniques that minimize the need for any actual shortest path computations.

How to improve the modeling efficiency and accuracy has become a burning problem. The popularization of recommendation technique in E-Commerce provide us new trajectories that can be used for addressing the problem. In this paper, we propose a graph-based workflow recommendation for improving business process modeling. The start point is so-called "workflow repository" including a set of already developed process models. Graph mining method is used to extract the process patterns from the repository. Based on graph edit distance (GED) [2], we calculate the distance between patterns and the partial business process, viewed as reference model, which is under modeling and select the candidate nodes with smaller distances for recommendation. The performance study show its feasibility for practical uses.