Legal judgment prediction (LJP) is a fundamental task of legal artificial intelligence. It aims to automatically predict the judgment results of legal cases. Three typical subtasks are relevant law article prediction, charge prediction, and term-of-penalty prediction. Due to the wide range of potential applications, LJP has attracted a great deal of interest, prompting the development of numerous approaches. These methods mainly focus on building a more accurate representation of a case’s fact description in order to improve the performance of judgment prediction. They overlook, however, the practical judicial scenario in which human judges often compare similar law articles or possible charges before making a final decision. To this end, we propose a supervised contrastive learning framework for the LJP task. Specifically, we train the model to distinguish (1) various law articles within the same chapter of a Law and (2) similar charges of the same law article or related law articles. By this means, the fine-grained differences between similar articles/charges can be captured, which are important for making a judgment. Besides, we optimize our model by identifying cases with the same article/charge labels, allowing it to more effectively model the relationship between the case’s fact description and its associated labels. By jointly learning the LJP task with the aforementioned contrastive learning tasks, our model achieves better performance than the state-of-the-art models on two real-world datasets.

Incorporating knowledge graphs as auxiliary information to enhance recommendation systems can improve the representations learning of users and items. Recommendation methods based on knowledge graphs can introduce user–item interaction learning into the item graph, focusing only on learning the node vector representations within a single graph; alternatively, they can treat user–item interactions and item graphs as two separate graphs and learn from each graph individually. Learning from two graphs has natural advantages in exploring original information and interaction information, but faces two main challenges: (1) in complex graph connection scenarios, how to adequately mine the self-information of each graph, and (2) how to merge interaction information from the two graphs while ensuring that user–item interaction information predominates. Existing methods do not thoroughly explore the simultaneous mining of self-information from both graphs and effective interaction information, leading to the loss of valuable insights. Considering the success of contrastive learning in mining self-information and auxiliary information, this paper proposes a dual-graph contrastive learning recommendation method based on knowledge graphs (KGDC) to explore a more accurate representations of users and items in recommendation systems based on external knowledge graphs. In the learning process within the self-graph, KGDC strengthens and represents the information of different connecting edges in both graphs, and extracts the existing information more fully. In interactive information learning, KGDC reinforces the interaction relationship between users and items in the external knowledge graph, realizing the leading role of the main task. We conducted a series of experiments on three standard datasets, and the results show that the proposed method can achieve better results.

Incorporating knowledge graphs as auxiliary information to enhance recommendation systems can improve the representations learning of users and items. Recommendation methods based on knowledge graph can introduce user-item interaction learning into the item graph, focusing only on learning the node vector representations within a single graph; alternatively, they can treat user-item interactions and item graphs as two separate graphs and learn from each graph individually. Learning from two graphs has natural advantages in exploring original information and interaction information, but faces two main challenges: 1) in complex graph connection scenarios, how to adequately mine the self-information of each graph, and 2) how to merge interaction information from the two graphs while ensuring that user-item interaction information predominates. Existing methods do not thoroughly explore the simultaneous mining of self-information from both graphs and effective interaction information, leading to the loss of valuable insights. Considering the success of contrastive learning in mining self-information and auxiliary information, this paper proposes a dual-graph contrastive learning recommendation method based on knowledge graphs (KGDC) to explore a more accurate representations of users and items in recommendation systems based on external knowledge graphs. In the learning process within the self-graph, KGDC has strengthened and represented the information of different connecting edges in both graphs, and extracted the existing information more fully. In interactive information learning, KGDC reinforces the interaction relationship between users and items in the external knowledge graph, realizing the leading role of the main task. We have conducted a series of experiments on three standard datasets, and the results show that the proposed method can achieve better results.

Convolutional neural networks (CNNs) are widely utilized in image classification. Nevertheless, CNNs typically require substantial computational resources, posing challenges for deployment on resource-constrained edge devices and limiting the spread of AI-driven applications. While various pruning approaches have been proposed to mitigate this issue, they often overlook a critical fact that edge devices are typically tasked with handling only a subset of classes rather than the entire set. Moreover, the specific combinations of subcategories that each device must discern vary, highlighting the need for fine-grained task-specific adjustments. Unfortunately, these oversights result in pruned models that still contain unnecessary category redundancies, thereby impeding the potential for further model optimization and lightweight design. To bridge this gap, we propose a task-level customized pruning (TLCP) method via utilizing task-level information, i.e., class combination information relevant to edge devices. Specifically, TLCP first introduces channel control gates to assess the importance of each convolutional channel for individual classes. These class-level control gates are then aggregated through linear combinations, resulting in a pruned model customized to the specific tasks of edge devices. Experiments on various customized tasks demonstrate that TLCP can significantly reduce the number of parameters, by up to 33.9% on CIFAR-10 and 14.0% on CIFAR-100, compared to other baseline methods, while maintaining almost the same inference accuracy.

Unmanned Aerial Vehicle-assisted Edge Computing (UAV-EC) leverages UAVs as aerial edge servers to provide computation resources to user equipment (UE) in dynamically changing environments. A critical challenge in UAV-EC lies in making real-time adaptive offloading decisions that determine whether and how UE should offload tasks to UAVs. This problem is typically formulated as Mixed-Integer Nonlinear Programming (MINLP). However, most existing offloading methods sacrifice strategy timeliness, leading to significant performance degradation in UAV-EC systems, especially under varying wireless channel quality and unpredictable UAV mobility. In this paper, we propose a novel framework that enhances offloading strategy timeliness in such dynamic settings. Specifically, we jointly optimize offloading decisions, transmit power of UEs, and computation resource allocation, to maximize system utility encompassing both latency reduction and energy conservation. To tackle this combinational optimization problem and obtain real-time strategy, we design a Quality of Experience (QoE)-aware Online Offloading (QO2) algorithm which could optimally adapt offloading decisions and resources allocations to time-varying wireless channel conditions. Instead of directly solving MIP via traditional methods, QO2 algorithm utilizes a deep neural network to learn binary offloading decisions from experience, greatly improving strategy timeliness. This learning-based operation inherently enhances the robustness of QO2 algorithm. To further strengthen robustness, we design a Priority-Based Proportional Sampling (PPS) strategy that leverages historical optimization patterns. Extensive simulation results demonstrate that QO2 outperforms state-of-the-art baselines in solution quality, consistently achieving near-optimal solutions. More importantly, it exhibits strong adaptability to dynamic network conditions. These characteristics make QO2 a promising solution for dynamic UAV-EC systems.

Personalized search aims to improve user experience by tailoring search results to individual preferences. This paper introduces GBPS, a novel group-based personalized search framework that enhances search relevance by dynamically incorporating group user information. Unlike traditional approaches that rely on static, query-independent groupings based on shared clicks, GBPS forms user groups based on representation similarity, capturing deeper semantic connections between users. A hierarchical recurrent neural network (RNN) is employed to model user profiles, and multiple grouping strategies are explored to optimize representation similarities. Experiments on the AOL search log demonstrate that GBPS significantly outperforms some personalized search methods, with improvements of 1.65% in MAP, 1.65% in MRR, and 1.47% in P@1. These results highlight the potential of dynamically leveraging group information to enhance personalized search performance and address the limitations of static grouping methods.