The persistent challenges of data sparsity and class imbalance have long limited the development of recommender systems. Fortunately, line graph theory offers a novel perspective to overcome these issues. By transforming the user-item interaction bipartite graph into a line graph, the problems of data sparsity and class imbalance are elegantly reformulated as those of insufficient labeled nodes and imbalanced label distribution in the line graph domain. This reformulation allows us to directly apply mature techniques from node classification and imbalanced graph learning to address these core challenges. Inspired by this insight, we propose a Line Graph Data Augmentation (LGDA) strategy, which features two distinct characteristics. Firstly, it is a plug-and-play module that resolves data sparsity and imbalance without modifying the underlying recommendation framework. Secondly, it employs a targeted augmentation and confidence filtering mechanism to generate high-quality, balanced augmented data. Extensive experiments on four real-world datasets validate that LGDA effectively alleviates data sparsity and class imbalance, leading to significant improvements in both recommendation performance and system robustness.

The rapid proliferation of intelligent connected vehicles generates increasingly heterogeneous application data, imposing stringent requirements for low-latency processing under resource constraints in dynamic vehicular environments. While vehicular edge computing (VEC) has emerged as a promising solution, conventional approaches suffer from critical limitations: data-induced model bias, weak generalization, inability to handle stochastic conditions, and inadequate multi-UAV coordination. This paper proposes AMTO (Attention-based Multi-agent Task Offloading), a novel deep reinforcement learning framework that systematically addresses these challenges through four key innovations: (1) a multi-agent architecture enabling scalable UAV coordination without centralized control overhead; (2) an attention mechanism that dynamically weights critical environmental features such as data queue lengths and channel conditions; (3) a specialized state normalization algorithm handling heterogeneous parameter scales (battery levels in kilojoules, distances in meters, data volumes in megabytes); and (4) a centralized training with decentralized execution paradigm for coordinated learning and autonomous deployment. We instantiate AMTO using Deep Deterministic Policy Gradient (DDPG) to handle continuous action spaces for joint optimization of offloading ratios and UAV trajectories. Through multi-objective reward functions balancing latency, energy efficiency, and quality-of-service, AMTO achieves distributed resource allocation that effectively reduces both delay and energy consumption. Extensive simulations demonstrate that AMTO converges 33% faster and achieves 28% latency reduction in high-density scenarios compared to vanilla DDPG, Actor-Critic, DQN, and traditional heuristic methods.

Keyphrase extraction (KPE) aims to automatically identify salient phrases that encapsulate a document's core concepts. While previous method based on prompt learning employs prompt-guided encoder-decoder architectures, its performance exhibits significant sensitivity to manually designed linguistic templates. To address this limitation, we propose a novel unsupervised KPE framework Pre-trained Prompt Rank (PTPRank). Specifically, PTPRank deploys our self-supervised model PromptT5 to dynamically generate domain-aware prompt templates through trainable parameters, eliminating the need for manual template engineering. Furthermore, we introduce a Discrete Wavelet Transformation (DWT) module to suppressing attention noise while preserving semantically critical patterns. During candidate ranking, we synergistically combine the model's generation probabilities with a novel Relevance Score metric that quantifies statistical salience through term distribution analysis. Comprehensive evaluations across six benchmark datasets demonstrate that PTPRank performs on a par with the latest large-language-model-based SOTA method.

The recommendation of long-tail items has been a persistent issue in recommender system research. The primary reason for this problem is that the model cannot learn better item features due to the lack of interactive record data of tail items, which leads to a decline in the model's recommendation performance. Existing methods transfer the features of the head items to the tail items, thereby ignoring their differences and failing to produce a satisfactory recommendation effect. To address the issue, we propose a novel recommendation model called MetaGA based on metalearning. The MetaGA model obtains initial parameters from head items through metalearning and fine-tunes model parameters during the learning process of tail item features. Additionally, it employs a graph convolutional network and attention mechanism to enhance tail data and reduce the difference between head and tail data. Through the above two steps, the model utilizes the abundant data of the head items to address the problem of sparse data of the tail items, resulting in improved recommendation performance. We conducted extensive experiments on three real-world datasets, and the results demonstrate that our proposed MetaGA model significantly outperforms other state-of-the-art baselines for tail item recommendation.

The integration of artificial intelligence has become a hot topic in the field of education. However, current studies primarily focus on personalization for learners, with the aim of accurately modeling learners’ knowledge level based on their learning history and providing better personalized services, while overlooking the needs of educators. In contrast to the focus on personalization of learners, educators place greater emphasis on accurately assessing collective performance and relative differences within a group, which serves as a qualitative measure of the teaching quality. In this study, we investigate collective knowledge tracing (CeKT), a method designed to estimate the average knowledge level of all students in a course based on a sequence of exercises. To achieve this objective, we propose a graph-based solution capable of estimating the average knowledge level solely from the exercise sequence as well as capturing the intrinsic structure of the exercise sequence (i.e., the sequential order of exercises and the repetition of exercises). Through experimental validation, we affirm that our approach enables a precise estimation of the average knowledge mastery of all students given an exercise sequence and also holds distinct value in three applications within the education domain.

Nowadays, the learning management system (LMS) has been widely used in different educational stages from primary to tertiary education for student administration, documentation, tracking, reporting, and delivery of educational courses, training programs, or learning and development programs. Towards effective learning outcome assessment, the exam script generation problem has attracted many attentions recently. But the research in this field is still in its early stage. Two essential issues have been ignored largely by existing solutions. First, given a course, it is unknown yet how to generate an quality exam script which concurrently has (i) the proper difficulty level, (ii) the coverage of essential knowledge points, (iii) the capability to distinguish academic performances between students, and (iv) the student scores in normal distribution. Second, while frequently encountered in practice, it is unknown so far how to generate a pair of high quality exam scripts which are equivalent in assessment (i.e., the student scores are comparable by taking either of them) but have significantly different sets of questions. To fill the gap, this paper proposes ExamGAN (Exam Script Generative Adversarial Network) to generate high quality exam scripts, and then extends ExamGAN to T-ExamGAN (Twin-ExamGAN) to generate a pair of high quality exam scripts. Based on extensive experiments on three benchmark datasets, it has verified the superiority of proposed solutions in various aspects against the state-of-the-art. Moreover, we have conducted a case study which demonstrated the effectiveness of proposed solution in the real teaching scenarios.