Knowledge Tracing (KT) aims to dynamically model a student’s mastery of knowledge concepts based on their historical learning interactions. Most current methods rely on single-point estimates, which cannot distinguish true ability from outburst or carelessness, creating ambiguity in judging mastery. To address this issue, we propose a Knowledge Mastery-State Disambiguation for Knowledge Tracing model (KeenKT), which represents a student’s knowledge state at each interaction using a Normal-Inverse-Gaussian (NIG) distribution, thereby capturing the fluctuations in student learning behaviors. Furthermore, we design an NIG-distance-based attention mechanism to model the dynamic evolution of the knowledge state. In addition, we introduce a diffusion-based denoising reconstruction loss and a distributional contrastive learning loss to enhance the model’s robustness. Extensive experiments on six public datasets demonstrate that KeenKT outperforms state-of-the-art KT models in terms of prediction accuracy and sensitivity to behavioral fluctuations. The proposed method yields the maximum AUC improvement of 5.85% and the maximum ACC improvement of 6.89%.

Multi-modal entity alignment aims to identify equivalent entities between two multi-modal Knowledge graphs by integrating multi-modal data, such as images and text, to enrich the semantic representations of entities. However, existing methods may overlook the structural contextual information within each modality, making them vulnerable to interference from shallow features. To address these challenges, we propose MyGram, a \textbf{m}odalit\textbf{y}-aware \textbf{gra}ph transformer with global distribution for \textbf{m}ulti-modal entity alignment. Specifically, we develop a modality diffusion learning module to capture deep structural contextual information within modalities and enable fine-grained multi-modal fusion. In addition, we introduce a Gram Loss that acts as a regularization constraint by minimizing the volume of a 4-dimensional parallelotope formed by multi-modal features, thereby achieving global distribution consistency across modalities. We conduct experiments on five public datasets. Results show that MyGram outperforms baseline models, achieving a maximum improvement of 4.8\% in Hits@1 on FBDB15K, 9.9\% on FBYG15K, and 4.3\% on DBP15K.

Visual Question Answering (VQA) requires models to reason over multimodal information, combining visual and textual data. With the development of continual learning, significant progress has been made in retaining knowledge and adapting to new information in the VQA domain. However, current methods often struggle with balancing knowledge retention, adaptation, and robust feature representation. To address these challenges, we propose a novel framework with adaptive memory allocation and global noise filtering called MacVQA for visual question answering. MacVQA fuses visual and question information while filtering noise to ensure robust representations, and employs prototype-based memory allocation to optimize feature quality and memory usage. These designs enable MacVQA to balance knowledge acquisition, retention, and compositional generalization in continual VQA learning. Experiments on ten continual VQA tasks show that MacVQA outperforms existing baselines, achieving 43.38% average accuracy and 2.32% average forgetting on standard tasks, and 42.53% average accuracy and 3.60% average forgetting on novel composition tasks.

Inductive reasoning aims to infer missing knowledge for unseen entities and relations. Existing methods exhibit limited generalization capabilities due to their dependence on localized structural patterns and inadequate handling of graph imbalance. To address these challenges, we propose a novel Hi erarchical Mod eling with Graph Perturbation-Enhanced Network (HiMod), which effectively integrates hierarchical relation modeling with a dynamic perturbation mechanism to enhance the generalization ability of inductive reasoning models. HiMod leverages a hierarchical relation modeling mechanism that maps specific relations to higher-level general concepts within a global semantic framework. This allows for capturing semantic commonalities across relations, enabling robust reasoning for unseen queries. Simultaneously, a dynamic perturbation mechanism is introduced to adjust perturbation strength based on node importance and graph sparsity, facilitating deeper exploration of the latent semantic space and mitigating the effects of graph imbalance. Extensive experiments on three benchmark inductive knowledge graph reasoning datasets demonstrate that HiMod achieves the most significant MRR improvements among the four split versions, with 11.17% on WN18RR, 4.61% on FB15K-237, and 5.47% on NELL-995. Our code is available at https://github.com/HubuKG/HiMod .

Visual Question Answering (VQA) presents a unique challenge by requiring models to understand and reason about visual content to answer questions accurately. Existing VQA models often struggle with biases introduced by the training data, leading to over-reliance on superficial patterns and inadequate generalization to diverse questions and images. This paper presents a novel model, IOG-VQA, which integrates Object Interaction Self-Attention and GAN-Based Debiasing to enhance VQA model performance. The self-attention mechanism allows our model to capture complex interactions between objects within an image, providing a more comprehensive understanding of the visual context. Meanwhile, the GAN-based debiasing framework generates unbiased data distributions, helping the model to learn more robust and generalizable features. By leveraging these two components, IOG-VQA effectively combines visual and textual information to address the inherent biases in VQA datasets. Extensive experiments on the VQA-CP v1 and VQA-CP v2 datasets demonstrate that our model shows excellent performance compared with the existing methods, particularly in handling biased and imbalanced data distributions highlighting the importance of addressing both object interactions and dataset biases in advancing VQA tasks. Our code is available athttps://github.com/HubuKG/IOG-VQA.

Multimodal knowledge graphs (MMKG) store structured world knowledge enriched with multimodal descriptive information. However, MMKG often faces the challenge of incompleteness. The primary objective of multimodal knowledge graph completion (MMKGC) is to predict missing entities within MMKG. Current MMKGC methods struggle with addressing the issue of over-trust attention and how to enhance the robustness of the model. To overcome these problems, we introduce APKGC, a noise-enhanced multimodal method for knowledge graph completion with attention penalty. APKGC effectively adjusts the attention scores in the language model and alleviates over-trust attention through a specifically designed attention penalty module. Additionally, an adaptive noise sampling module is proposed to supplement the entity's multimodal information, thereby enhancing the model's robustness. Experimental evaluation demonstrates that APKGC excels in overcoming these challenges. Compared to the existing state-of-the-art MMKGC model, APKGC improves Hit@1 by 3.3% on the DB15K dataset and by 3.4% on the MKG-W dataset.

Learning concept prerequisite relations helps better master and build a logically coherent knowledge structure. Many studies use graph neural networks to create heterogeneous knowledge networks that enhance concept representations. However, different types of relations in these networks can influence each other. Existing research often focuses solely on concept relations, neglecting other types of knowledge connections. To address this issue, this paper proposes a novel concept prerequisite relation learning model, named the Global Knowledge Relation Optimization Model(GKROM). Specifically, we capture the impact of different knowledge relation types on document and concept semantic representations separately, integrating the document and concept semantic representations. Then, we introduce multi-objective learning to optimize the knowledge relation network from a global perspective. Through the above optimization, GKROM learns richer semantic representations for concepts and documents, improving the accuracy of concept prerequisite relation learning. Extensive experiments on public datasets demonstrate the effectiveness of our GKROM, achieving state-of-the-art performance in concept prerequisite relation learning.

Concept prerequisite relations determine the learning order of knowledge concepts in one domain, which has an important impact on teachers' course design and students' personalized learning. Current research usually predicts concept prerequisite relations from the perspective of knowledge, and rarely pays attention to the role of learners' learning behavior. We propose a Dual Graph Distillation Method for Concept Prerequisite Relation Learning (DGCPL). Specifically, DGCPL constructs a dual graph structure from both the knowledge and learning behavior perspectives, and captures the high-order knowledge features and learning behavior features through the concept-resource hypergraph and the learning behavior graph respectively. In addition, we introduce a gated knowledge distillation to fuse the structural information of concept nodes in the two graphs, so as to obtain a more comprehensive concept embedding representation and achieve accurate prediction of prerequisite relations. On three public benchmark datasets, we compare DGCPL with eight graph-based baseline methods and five traditional classification baseline methods. The experimental results show that DGCPL achieves state-of-the-art performance in learning concept prerequisite relations. Our code is available at https://github.com/wisejw/DGCPL.

Knowledge tracing (KT) is essential in education for enhancing student learning by forecasting future performance based on historical data. However, current deep learning KT models often inadequately capture latent factors in students’ responses. Moreover, the commonly used neural network architectures in these models tend to lack interpretability, which can detract from understanding the underlying mechanics of the predictions. Our proposed KANOptiKT model alleviates these limitations by employing a matrix factorization approach to model implicit question difficulty and student ability from interaction records. Additionally, we introduce the Kolmogorov-Arnold Network (KAN) into the KT domain, enhancing both the accuracy and interpretability of the model. Specifically, we improve the attention mechanism using the optimized KAN as a way to better handle multi-feature interactions and further feature learning and model training through KAN. Furthermore, the training cost of the proposed KANOptiKT is remarkably efficient when compared to baseline models, as verified through our experiments. Experimental results from three widely used public datasets demonstrate that KANOptiKT outperforms existing knowledge tracing models in terms of both accuracy and interpretability. We also validate the effectiveness of KANOptiKT through ablation study, demonstrating the contribution of each component of the model.

For the Internet of Vehicles (IoV), driving safety applications require reliable and up-to-date knowledge of the state of vehicles and traffic. A single vehicle cannot meet all the reliability requirements because of the limited capability of information acquisition. Thus, cooperation among vehicles for information sharing is essential. However, due to the high dynamic network topology and harsh channel conditions, maintaining long-term cooperation is not feasible. Only the messages that most affect the driving state can obtain the transmission opportunity for avoiding network congestion. In this paper, we propose a cooperative safety-enhanced control framework (SCF). This framework concentrates on the construction of dynamic and adaptive cooperation among vehicles and evaluates the key feature parameters to achieve an optimal safety utility for feedback control over the driving state. We construct a general multi-layer solution framework for driving assistance in SCF. First, we construct multiple temporary cooperative platoons to coordinate adjacent vehicles and realize a relatively uniform driving state. The cooperative platoon maintains short-term stability for vehicle sensing and tracing. Second, we propose a utility evaluation model for extracting the key feature parameters related to the driving state, which is the basis of the optimization for message transmission and driving control. Third, we design a two-level joint optimization mechanism for the deep fusion of the multi-source heterogeneous data to maximize the total utility of driving safety. Finally, we propose an adaptive feedback control model for the cooperative platoon, which actively adjusts the driving control strategy and the message transmission strategy in a real-time manner. Then the optimal driving assistant decision can be made. Extensive simulation results show that SCF outperforms related communication mechanisms for safe driving in the IoV, demonstrating that SCF can effectively enhance driving assistance control.

Concept prerequisite relation learning is used to identify dependency relations between knowledge concepts, which helps learners choose effective learning paths. Currently, most of the mainstream methods utilise deep learning algorithms to capture the prerequisite relations between concepts through supervised or semi-supervised learning. However, these methods are highly dependent on labelled data, which is scarce and costly to annotate in reality. To address this problem, we propose a framework calledWeaklySupervisedEnhancedConceptPrerequisiteRelationLearning (WSECPRL). Specifically, we first generate an enhanced concept pseudo-relation graph without labeled data using the pre-trained language model and the large knowledge base as auxiliary information. Second, we propose an improved variational graph auto-encoder model to correctly determine the concept prerequisite relations. We incorporate a multi-head attention mechanism to enhance the representation learning capability of weakly supervised learning. The model reconstructs a directed graph into multiple undirected graphs by splitting the adjacency matrix and determines the direction of the concept prerequisite relation based on the strength of the dependency relation between concepts. Finally, experimental results on several publicly available datasets demonstrate the effectiveness of our proposed framework, with WSECPRL outperforming existing baseline models in terms of F1 scores and AUC.

Knowledge graphs (KGs) are frequently confronted with the challenge of incompleteness, a problem that extends to multimodal knowledge graphs (MKGs). The primary goal of multimodal knowledge graph completion (MKGC) is to predict missing entities within MKGs. However, current MKGC methods face difficulties in adequately addressing modal preferences and imbalances in modal information. To overcome these issues, we introduce AdaMKGC, an innovative hybrid model incorporating an adaptive modality interaction transformer. This model employs a dynamic attention interaction strategy and a self-enhancing sampling approach. AdaMKGC achieves a more precise utilization of multimodal information by integrating modal preference information into modal interactions. Additionally, it effectively mitigates the issue of modal imbalance through targeted sampling and adjustment for entities with deficient information. Experimental evaluations demonstrate AdaMKGC’s superior performance in overcoming these prevalent challenges. Compared to existing state-of-the-art MKGC models, AdaMKGC shows a notable enhancement of 28% in MR on the WN18-IMG dataset and an improvement of 2.7% in Hits@1 on the FB15k-237-IMG dataset. Our code is available at https://github.com/HubuKG/AdaMKGC .

Epilepsy, a widespread neurological disorder, creates substantial physical and psychological challenges for patients. Accurate seizure prediction allows for prompt symptom intervention and treatment guidance. To achieve this goal, we introduce a classification model for epilepsy using variational mode quadratic decomposition. It first processes EEG signals from epilepsy patients with variational mode decomposition. Then, a second variational mode decomposition filters and breaks down the residual signal further. After decomposition, signals are reconstructed into continuous wavelet transform feature images. A combination of convolutional neural network and temporal convolutional network then classifies epileptic seizure periods, including ictal, preictal, interictal, and non-ictal phases. The extensive experimental results show the model reaches 85% accuracy and 88.8% precision in classifying epileptic seizure, pre-ictal, inter-ictal, and non-ictal periods, evidencing the proposed method's effectiveness.

Nowadays, the high dropout rate has become a widespread phenomenon in various MOOC platforms. When learning a MOOC, many learners are reluctant to spend time learning from the first video lecture to the last one. If we can recommend a learning path based on learners' individual needs and ignore irrelevant video lectures in the MOOC, it will help them learn more efficiently. The premise of learning path recommendation is to understand the precedence relations between learning resources. In this paper, we propose a novel approach for extracting precedence relations between video lectures in a MOOC. According to "knowledge depth" of concepts, we extract the core concepts from the video captions accurately. Transformer-based models are used to discover concept prerequisite relations, which help us identify the precedence relations between video lectures in MOOCs. Experiments show that the proposed method outperforms the state-of-the-art methods.

Today, the Internet is flooded with a lot of learning resources, which are provided by different people. Because the relationship between these learning resources is unclear, it is difficult for instructors and students to use these learning resources for curriculum design and learning path planning. The order of learning resources is usually determined by the core knowledge concepts addressed in each resource. Therefore, identifying the prerequisite relations between concepts will be the key to solving the above problems. In this article, we take Wikipedia as an example and propose a new method for identifying concept prerequisite relations. We define five groups of features for concept pairs and predict whether there is a prerequisite relations between two concepts. Experimental results show that the performance of the proposed method exceeds the existing baselines.

Nowadays, online learning is becoming more and more popular. Various online learning platforms provide a huge amount of learning resources for learners around the world. When choosing or sorting learning resources, learners often need to know what important knowledge concepts are addressed in each learning resource. Exploring the prerequisite relations among concepts is of great significance to educational planning. In this paper, we extracted concepts from the content of course descriptions and proposed a new approach that uses both course-based features and Wikipedia-based features to discover the prerequisite relations between knowledge concepts. Experiments on both English and Chinese datasets show that the proposed method outperforms existing baselines.

Affected by the COVID-19 pandemic, teaching tasks have gradually shifted from offline to online, which expanded online education resources unprecedentedly."Concept" is a professional vocabulary in the curriculum.Exploring the prerequisite relations among concepts is of great significance to educational planning.This research extracts concepts from online course introduction and proposes a mixed method for extracting concept prerequisite relations.Experiments on public data set show that this method outperforms existing ones.Tests were also carried out on the datasets of eleven schools, which proves that this model has good scalability.

Online educational resources usually provided by different people, and the dependency relations between resources are always not clear, which bring challenges for self-directed learners, since they don't know where to begin when they have a collection of resources. Concept prerequisite relations play an important role in educational resources sequencing and curriculum planning tasks. In this paper, we treat Wikipedia as an educational resource corpus and propose an ensemble learning approach for extracting concept prerequisite relations from Wikipedia. In experiments, we evaluate our approach on two existing datasets, the CMU and AL-CPL datasets, and validate that our approach can achieve better performance than baseline methods.

Extracting prerequisite relations among concepts is helpful for users to find out the background knowledge and determine reading order in a corpus. We investigate the problem and propose an effective method and multiple features to capture prerequisite relations between concepts in Wikipedia. Our experiments on eight datasets from both English and Chinese Wikipedia show that the proposed method outperforms existing prerequisite learning methods.