Search

Graph embedding has gained significant popularity due to its ability to represent large-scale graph data by mapping nodes to a low-dimensional space. However, most of the existing research in this field has focused on transductive learning, where fixed node embeddings are generated by training the entire graph. This approach is not well-suited for temporal graphs that undergo continuous changes with the addition of new nodes and interactions. To address this limitation, we propose an inductive temporal graph embedding method called MIAN (Multi-angle Information Aggregation Network). The key focus of MIAN is to design an aggregation function that combines multi-angle information for generating node embeddings. Specifically, we divide the information into different angles, including neighborhood, temporal, and environment. Each angle of information is modeled and mined independently, and then fed into an improved gated recuttent unit (GRU) module to effectively combine them. To assess the performance of MIAN, we conduct extensive experiments on various real-world datasets and compare its results with several state-of-the-art baseline methods across diverse tasks. The experimental findings demonstrate that MIAN outperforms these methods. [ABSTRACT FROM AUTHOR]

Benefits of self-testing for learning have been consistently shown for simple materials such as word lists learned by rote memorization. Considerably less evidence for such benefits exists for complex, more educationally relevant materials and its application to new situations. The present study explores the mechanisms underlying this transfer. To this end, a typical retrieval-practice-effect paradigm was applied to foster the learning of an artificial language. Participants either repeatedly studied grammatically correct exemplar sentences of the artificial language or engaged in a cloze test as the interim test after learning. To assess far transfer, participants in both groups of restudy and retrieval practice engaged in a grammaticality judgment test after a delay of 5 min and 1 week. In addition, participants in both groups completed a final memory test (i.e., a cloze test identical to the initial test) 1 week after learning. In addition to a long-term memory benefit of retrieval practice, results revealed also a retrieval-practice benefit in the far-transfer test after the 1-week delay. The findings further support the view that far transfer is supported by learning the underlying grammatical rules as opposed to memorizing the material. Thus, retrieval practice is also effective for fostering learning of complex materials and, even more importantly, for promoting transfer of learning—a crucial goal in modern educational practices. [ABSTRACT FROM AUTHOR]

Network science has witnessed a surge in popularity, driven by the transformative power of node representation learning for diverse applications like social network analysis and biological modeling. While shallow embedding algorithms excel at capturing network structure, they face a critical limitation—failing to generalize to unseen nodes. This paper addresses this challenge by introducing Inductive Shallow Node Embedding—as a main contribution—pioneering a novel approach that extends shallow embeddings to the realm of inductive learning. It has a novel encoder architecture that captures the local neighborhood structure of each node, enabling effective generalization to unseen nodes. In the generalization, robustness is essential to avoid degradation of performance arising from noise in the dataset. It has been theoretically proven that the covariance of the additive noise term in the proposed model is inversely proportional to the cardinality of a node's neighbors. Another contribution is a mathematical lower bound to quantify the robustness of node embeddings, confirming its advantage over traditional shallow embedding methods, particularly in the presence of parameter noise. The proposed method demonstrably excels in dynamic networks, consistently achieving over 90% performance on previously unseen nodes compared to nodes encountered during training on various benchmarks. The empirical evaluation concludes that our method outperforms competing methods on the vast majority of datasets in both transductive and inductive tasks. [ABSTRACT FROM AUTHOR]

Abstract Benefits of self-testing for learning have been consistently shown for simple materials such as word lists learned by rote memorization. Considerably less evidence for such benefits exists for complex, more educationally relevant materials and its application to new situations. The present study explores the mechanisms underlying this transfer. To this end, a typical retrieval-practice-effect paradigm was applied to foster the learning of an artificial language. Participants either repeatedly studied grammatically correct exemplar sentences of the artificial language or engaged in a cloze test as the interim test after learning. To assess far transfer, participants in both groups of restudy and retrieval practice engaged in a grammaticality judgment test after a delay of 5 min and 1 week. In addition, participants in both groups completed a final memory test (i.e., a cloze test identical to the initial test) 1 week after learning. In addition to a long-term memory benefit of retrieval practice, results revealed also a retrieval-practice benefit in the far-transfer test after the 1-week delay. The findings further support the view that far transfer is supported by learning the underlying grammatical rules as opposed to memorizing the material. Thus, retrieval practice is also effective for fostering learning of complex materials and, even more importantly, for promoting transfer of learning—a crucial goal in modern educational practices.

Abstract Network science has witnessed a surge in popularity, driven by the transformative power of node representation learning for diverse applications like social network analysis and biological modeling. While shallow embedding algorithms excel at capturing network structure, they face a critical limitation—failing to generalize to unseen nodes. This paper addresses this challenge by introducing Inductive Shallow Node Embedding—as a main contribution—pioneering a novel approach that extends shallow embeddings to the realm of inductive learning. It has a novel encoder architecture that captures the local neighborhood structure of each node, enabling effective generalization to unseen nodes. In the generalization, robustness is essential to avoid degradation of performance arising from noise in the dataset. It has been theoretically proven that the covariance of the additive noise term in the proposed model is inversely proportional to the cardinality of a node’s neighbors. Another contribution is a mathematical lower bound to quantify the robustness of node embeddings, confirming its advantage over traditional shallow embedding methods, particularly in the presence of parameter noise. The proposed method demonstrably excels in dynamic networks, consistently achieving over 90% performance on previously unseen nodes compared to nodes encountered during training on various benchmarks. The empirical evaluation concludes that our method outperforms competing methods on the vast majority of datasets in both transductive and inductive tasks.

The interaction between T-cell receptors (TCRs) and peptides (epitopes) presented by major histocompatibility complex molecules (MHC) is fundamental to the immune response. Accurate prediction of TCR–epitope interactions is crucial for advancing the understanding of various diseases and their prevention and treatment. Existing methods primarily rely on sequence-based approaches, overlooking the inherent topology structure of TCR–epitope interaction networks. In this study, we present |$GTE$|⁠ , a novel heterogeneous Graph neural network model based on inductive learning to capture the topological structure between TCRs and Epitopes. Furthermore, we address the challenge of constructing negative samples within the graph by proposing a dynamic edge update strategy, enhancing model learning with the nonbinding TCR–epitope pairs. Additionally, to overcome data imbalance, we adapt the Deep AUC Maximization strategy to the graph domain. Extensive experiments are conducted on four public datasets to demonstrate the superiority of exploring underlying topological structures in predicting TCR–epitope interactions, illustrating the benefits of delving into complex molecular networks. The implementation code and data are available at https://github.com/uta-smile/GTE. [ABSTRACT FROM AUTHOR]

Graph embedding has gained significant popularity due to its ability to represent large-scale graph data by mapping nodes to a low-dimensional space. However, most of the existing research in this field has focused on transductive learning, where fixed node embeddings are generated by training the entire graph. This approach is not well-suited for temporal graphs that undergo continuous changes with the addition of new nodes and interactions. To address this limitation, we propose an inductive temporal graph embedding method called MIAN (Multi-angle Information Aggregation Network). The key focus of MIAN is to design an aggregation function that combines multi-angle information for generating node embeddings. Specifically, we divide the information into different angles, including neighborhood, temporal, and environment. Each angle of information is modeled and mined independently, and then fed into an improved gated recuttent unit (GRU) module to effectively combine them. To assess the performance of MIAN, we conduct extensive experiments on various real-world datasets and compare its results with several state-of-the-art baseline methods across diverse tasks. The experimental findings demonstrate that MIAN outperforms these methods.

Accurately analyzing the flow and transport behavior in a large discrete fracture network is computationally expensive. Fortunately, recent research shows that most of the flow and transport occurs within a small backbone in the network, and identifying the backbone to replace the original network can greatly reduce computational consumption. However, the existing machine learning based methods mainly focus on the features of the fracture itself to evaluate the importance of the fracture, the local structural information of the fracture network is not fully utilized. More importantly, these machine learning methods can neither control the identified backbone's size nor ensure the backbone's connectivity. To solve these problems, a deep learning model named multi-aggregator graph neural network (MA-GNN) is proposed for identifying the backbone of discrete fracture networks. Briefly, MA-GNN uses multiple aggregators to aggregate neighbors' structural features and thus generates an inductive embedding to evaluate the criticality score of each node in the entire fracture network. Then, a greedy algorithm, which can control the backbone's size and connectivity, is proposed to identify the backbone based on the criticality score. Experimental results demonstrate that the backbone identified by MA-GNN can recover the transport characteristics of the original network, outperforming state-of-the-art baselines. In addition, MA-GNN can identify influential fractures with higher Kendall's τ correlation coefficient and Jaccard similarity coefficient. With the ability of size control, our proposed MA-GNN can provide an effective balance between accuracy and computational efficiency by choosing a suitable backbone size. [ABSTRACT FROM AUTHOR]

Recent studies suggest that making judgments of learning (JOLs)—self-assessment of current learning status—may not merely be a neutral cognitive process, but can directly improve learning through what is called ‘JOL reactivity’. This study investigated whether making JOLs can facilitate the learning of previously studied materials (backward effect) and newly studied materials (forward effect) in inductive learning. We also examined how this effect varies depending on whether a JOL is accompanied by a retrieval attempt. Across three experiments, participants learned about various butterfly species presented in two sections (Sections A and B). Some participants made JOLs between Section A and Section B, while others did not, and then all participants took a final transfer test for both sections. In Experiment 1, merely making JOLs did not facilitate learning compared to restudy control, regardless of whether JOLs afforded covert retrieval (target-absent JOL) or not (target-present JOL). However, in Experiment 2, when participants made JOLs combined with overt retrieval prompts (retrieval practice + JOL), they outperformed the other groups in the final transfer test of Section B, showing the forward effect. Experiment 3 further revealed that the act of making JOLs combined with overt retrieval practice was as effective as (but not more than) retrieval practice without JOLs in promoting new learning. Our findings indicate that conventional forms of JOLs do not appear to enhance inductive learning; rather, they underscore the critical role of retrieval in facilitating inductive learning. [ABSTRACT FROM AUTHOR]

This research used web-based inductive learning that facilitated plane geometry learning, where the learning was carried out online. It was hypothesized that students could learn the concept of plane geometry better when students were involved in the induction process with the help of GeoGebra software. They did explore with GeoGebra software to form several examples of the concept, testing the patterns that existed in the examples, and generalized the findings into new knowledge. With the help of the web and GeoGebra software, students could carry out their own learning and make their own discoveries. To test the effectiveness of web-based inductive learning, two classes were involved in the research, they were students of the Mathematics education study program Faculty of Teacher Training and Education, University of Bengkulu who took plane geometry class in the even semester of the 2021/2022 academic year as many as 68 students. This research was a quasi-experimental research with a post-test-only control group design. The instrument used for measurement was a description test. Based on the data analysis, it was found that the learning outcomes using web-based inductive learning assisted on GeoGebra were better than those using the expository method. [ABSTRACT FROM AUTHOR]

Knowledge graph completion can make knowledge graph more complete. However, traditional knowledge graph completion methods assume that all test entities and relations appear in the training process. Due to the evolving nature of real world KG, once unseen entities or relations appear, the knowledge graph needs to be retrained. Inductive learning for knowledge graph completion aims to complete triples containing unseen entities or unseen relations without training the knowledge graph from scratch, so it has received much attention in recent years. Firstly, starting from the basic concept of knowledge graph, this paper divides knowledge graph completion into two categories: transductive and inductive. Secondly, from the theoretical perspective of inductive knowledge graph completion, it is divided into two categories: semi-inductive and fully-inductive, and the models are summarized from this perspective. Then, from the technical perspective of inductive knowledge graph completion, it is divided into two categories: based on structural information and based on additional information. The methods based on structural information are subdivided into three categories: based on inductive embedding, based on logical rules and based on meta learning, and the methods based on additional information are subdivided into two categories: based on text information and other information. The current methods are further subdivided, analyzed and compared. Finally, it forecasts the main research directions in the future.

Despite the fact that there is generally an agreement on the irreplaceable role of the ethical component in social work education, our understanding of values in social work education still remains quite limited. The article aims to analyse, from the perspective of educators, the instilling of social work values at the Czech, Slovakian, Polish and Hungarian universities. Research findings allows to identify its types, threats and limitations and to indicate steps for its enhancement and for the implementation of the systemic concept of the values instilling education. The implications for social work education are as follows: to critically reflect the external threats and limits created by neoliberalism and its values; to critically reflect the internal threats and limits caused by the absence of systemic values education in some social work study programmes; to promote a systemic concept of values instilling education and consistently implement the inductive learning and integrated approach in values building in subjects included in the social work study programmes. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Frontiers of Computer Science & Technology is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Recent research efforts on Few-Shot Learning (FSL) have achieved extensive progress. However, the existing efforts primarily focus on the transductive setting of FSL, which is heavily challenged by the limited quantity of the unlabeled query set. Although a few inductive-based FSL methods have been studied, most of them emphasize learning superb feature extraction networks. As a result, they may ignore the relations between sample-level and class-level representations, which are particularly crucial when labeled samples are scarce. This paper proposes an inductive FSL framework that leverages the Hierarchical Knowledge Propagation and Distillation, named HKPD. To learn more discriminative sample-level representations, HKPD first constructs a sample-level information propagation module that explores pairwise sample relations. Subsequently, a class-level information propagation module is designed to obtain and update the class-level information. Moreover, a self-distillation module is adopted to further improve the learned representations by propagating the obtained knowledge across this hierarchical architecture. Extensive experiments conducted on the commonly used few-shot benchmark datasets demonstrate the superiority of the proposed HKPD method, which outperforms the current state-of-the-art methods. • We highlight the significance of the inductive Few-Shot Learning in the real-world settings. • The existing inductive FSL methods usually ignore the relations between sample-level and class-level representations. • The proposed HKPD can leverage these relations, designed for the inductive setting. • A self-distillation module is designed to further improve the performance. [ABSTRACT FROM AUTHOR]

Demands for more accurate machine learning models have given rise to rethinking current modeling approaches that were deemed unsuitable, primarily due to their computational complexity and the lack of availability and accessibility to representative data. In Industry 4.0, rapid advancements in Digital Twin (DT) technologies and the pervasiveness of cost-effective sensor technologies have pushed the incorporation of artificial intelligence, particularly data-driven machine learning models, for use in smart manufacturing. However, the persistent issue with such models is their high sensitivity to the training data and the lack of interpretability in the outcomes, at times generating unrealistic results. The incorporation of knowledge into the machine learning pipeline has been earmarked as the most promising approach to address such issues. This paper aims to answer this call through a Knowledge-embedded Machine Learning (KML) framework for smart manufacturing, which embeds knowledge from experience and, or physics information into the machine learning pipeline, thus making the outcomes from these models more representative of real applications. The merits of KML were then presented through comparative studies showing its capability to outperform knowledge-based and data-driven models. This promising outcome led to the development of frameworks that can potentially incorporate KML for smart manufacturing applications such as Prognostics and Health Management (PHM) and DT, further supporting the usefulness of the proposed KML framework. [ABSTRACT FROM AUTHOR]

Research has demonstrated that L2 English learners' acquisition of grammar can be facilitated by Data-Driven Learning (DDL), which clearly promotes inductive learning and learner-centeredness (e.g. Boontam & Phoochaoroensil, 2018). This present study focuses on the impacts of DDL on Thai secondary and tertiary educators' introduction of English conditionals. The participants were taught using corpus-based DDL materials representing authentic use of conditionals for six weeks. It was shown in the interview results that DDL is useful and enhances learners' self-discovery of L2 grammar rules regarding conditionals. Not only does DDL enable learners to notice the three classic if-conditional types but also it allows them to explore alternative, i.e. mixed, types of conditionals, which are often overlooked by textbooks. Some concerns about the use of DDL in a broader context of ELT deal with school budgets and students' need of technical help. [ABSTRACT FROM AUTHOR]

Hierarchy network, as a type of complex graphs, is widely used in many application scenarios such as social network analysis in web, human resource analysis in e-government, and product recommendation in e-commerce. Hierarchy preserving network embedding is a representation learning method that project nodes into feature space by preserving the hierarchy property of networks. Recently, researches on network embedding are devoted to mining hierarchical structures and profit a lot form it. Among these works, SpaceNE stands out of preserving hierarchy with the help of subspace constraint on the hierarchical subspace system. However, like all other existing works, SpaceNE is based on transductive learning method and is hard to generalize to new nodes. Besides, they have high time complexity and hard to be scalable to large-scale networks. This paper proposes an inductive method, FastHGE to learn node representation more efficiently and generalize to new nodes more easily. As SpaceNE, a hierarchy network is embedded into a hierarchical subspace tree. For upper communities, we exploit transductive learning by preserving inner-subspace proximity of subspace from the same ancestor. For extending to new nodes, we adopt inductive learning to learn representations of leaf nodes. The overall representation of a node is retrieved by concatenating the embedding vectors of all its ancestor communities and the leaf node. By learning the basis vectors of subspace, the computing cost is alleviated from updating many parameters of projection matrices as in SpaceNE. The performance evaluation experiments show that FastHGE outperforms with much fast speed and the same accuracy. For example, in the node classification, FastHGE is nearly 30 times faster than SpaceNE. The source code of FastHGE is available online. [ABSTRACT FROM AUTHOR]

Participants performed a categorization training task, where each trial presented a claim based on an observation, and participants marked which fallacy or bias, if any, applied to the claim. In two studies, we measure the effect of this training task on critical thinking, measured using an open-ended critical thinking assessment. In Study 1, we pilot these materials in an online college course and observe credible improvements in critical thinking performance. In Study 2, we conduct a randomized controlled experiment and observe credible improvements in critical thinking relative to no training, and relative to comparable learning activities focused on conventional curricular content. We infer that the categorization training task facilitated inductive learning of patterns of biased and flawed reasoning, which improved participants' ability to identify such patterns in a delayed critical thinking assessment. Such categorization training shows promise as an effective and practical method for improving learners' resistance to online misinformation. General Audience Summary: Helping students learn to think critically is an important priority across education levels, but there is currently no clear consensus on how to teach critical thinking. Many proposed teaching strategies are very elaborate and involve extensive discussion and analysis, which makes it difficult for teachers to incorporate critical thinking instruction into their existing curriculum. In our current research, we explore whether a more focused approach might improve students' critical thinking performance. Specifically, we examine an inductive approach to critical thinking instruction. Inductive learning, commonly known as learning by example, happens when a person learns a general pattern from multiple examples of the pattern. In this case, we ask whether participants can learn to identify illogical or biased claims, a common measure of critical thinking ability, by presenting them with multiple examples of different kinds of fallacies and biases. We presented participants with sets of example scenarios in which an individual makes a claim based on an observation, and participants categorized which fallacy or bias, if any, the individual in the scenario was committing. In two studies, we find that this critical thinking categorization practice improves performance on a delayed open-ended critical thinking assessment. These exciting results show that critical thinking skills can be taught using a well established, specific, psychologically grounded method, and these results come at a critical juncture in our society. In a time of fake news, misinformation and a lack of critical thinking skills among the populace can have dire consequences. We believe our current results are of broad interest to educators and applied cognitive psychologists, and show promise for improving peoples' defenses against misinformation. [ABSTRACT FROM AUTHOR]

Cyber-attacks pose increasing challenges in precisely detecting intrusions, risking data confidentiality, integrity, and availability. This review paper presents recent IDS taxonomy, a comprehensive review of intrusion detection techniques, and commonly used datasets for evaluation. It discusses evasion techniques employed by attackers and the challenges in combating them to enhance network security. Researchers strive to improve IDS by accurately detecting intruders, reducing false positives, and identifying new threats. Machine learning (ML) and deep learning (DL) techniques are adopted in IDS systems, showing potential in efficiently detecting intruders across networks. The paper explores the latest trends and advancements in ML and DL-based network intrusion detection systems (NIDS), including methodology, evaluation metrics, and dataset selection. It emphasizes research obstacles and proposes a future research model to address weaknesses in the methodologies. The decision tree, known for its speed and user-friendliness, is proposed as a model for detecting result anomalies, combining findings from a comparative survey. This research aims to provide insights into building an effective decision tree-based detection framework.

La Elasticidad y Resistencia de Materiales (ERM) es una disciplina impartida en muchos grados de ingeniería. Esta asignatura necesita que los alumnos presenten una actitud participativa durante el proceso de aprendizaje, debido a su complejidad e importancia a lo largo del grado. Sin embargo, los estudiantes la encuentran muy complicada y abstracta. Por tanto, la principal dificultad que encuentra el profesor a la hora de enseñar es mantener el interés y motivación de los alumnos durante el proceso de aprendizaje. Para ayudar en esta tarea, los profesores deben ayudarse de nuevas metodologías como el aprendizaje basado en problemas y la clase inversa, donde se facilita la información a los estudiantes previamente a la clase presencial. En este trabajo, se presenta la aplicación de un aprendizaje basado en problemas al laboratorio de ERM en el grado de Ingeniería Mecánica. Además, para aumentar el entusiasmo y la motivación de los estudiantes, estas sesiones de laboratorio incluyeron una tecnología de fabricación innovadora, impresión 3D, y el empleo de correlación de imágenes digitales (DIC) para medida de desplazamientos y deformaciones. Antes de cada sesión práctica, se animaba a los alumnos a visualizar un vídeo online con los aspectos fundamentales de la práctica. Para evaluar el éxito de esta metodología, después de terminar las sesiones de laboratorio, los estudiantes respondieron una encuesta cuantitativa no formal. Los resultados mostraron que el aprendizaje basado en problemas propuesto tenía la capacidad de ayudar a integrar los conocimientos y mejorar la adquisición de las competencias incluidas en la guía docente de la asignatura. Aunque estos resultados son alentadores, todavía hay partes de la actividad de laboratorio que deben mejorarse para que la actividad consuma menos tiempo y facilitar las partes más complejas para los estudiantes. /// Elasticity and Strength of Materials is an elementary discipline across many engineering degrees. Students perceive it as very difficult and abstract and students’ active participation in the learning process is needed, due to its complexity and importance during the whole degree years. Hence, the main difficulty in teaching them is maintaining students' motivation and keeping their participation in the learning process. This is the reason to use new tools, such as problem-based learning (PBL) and flipped classroom, to help students understand and study the subject. In this work, we present the application of a problem-based learning to the lab in the Mechanical engineering degree, in of one the most time-consuming and difficult subjects of its program. Moreover, to enhance students’ enthusiasm and motivation, these sessions included an innovative manufacturing technology, 3D printing, and digital image correlation (DIC). Before each practical session, the students are encouraged to watch an online video with the fundamental aspects. In order to assess the success of this laboratory course, after finishing the lab sessions, the students answered a non-formal quantitative survey. The results showed that the proposed project-based learning had the ability to help integrating the knowledge and improve the skills included in the main competences. Although these results are encouraging, there are still parts of the lab activity that should be improve in order to make the activity less time consuming and the most difficult part being easier for the students.

The performance of optimization algorithms, and consequently of AI/machine learning solutions, is strongly influenced by the setting of their hyperparameters. Over the last decades, a rich literature has developed proposing methods to automatically determine the parameter setting for a problem of interest, aiming at either robust or instance-specific settings. Robust setting optimization is already a mature area of research, while instance-level setting is still in its infancy, with contributions mainly dealing with algorithm selection. The work reported in this paper belongs to the latter category, exploiting the learning and generalization capabilities of artificial neural networks to adapt a general setting generated by state-of-the-art automatic configurators. Our approach differs significantly from analogous ones in the literature, both because we rely on neural systems to suggest the settings, and because we propose a novel learning scheme in which different outputs are proposed for each input, in order to support generalization from examples. The approach was validated on two different algorithms that optimized instances of two different problems. We used an algorithm that is very sensitive to parameter settings, applied to generalized assignment problem instances, and a robust tabu search that is purportedly little sensitive to its settings, applied to quadratic assignment problem instances. The computational results in both cases attest to the effectiveness of the approach, especially when applied to instances that are structurally very different from those previously encountered. [ABSTRACT FROM AUTHOR]

Representation learning based on graph data has shown significant value for graph downstream tasks such as recommendation system and link prediction. However, current methods have some drawbacks: the fixed propagation of graph neural network limits the semantic expression of node representations, and encoder-decoder architecture with regularized reconstruction is prevented from learning differentiated features between nodes, which may lead to node representations not well suited to some graph downstream tasks. Therefore, a multi-level feature augmented graph representation learning model has been proposed via mutual information maximization, which is capable of learning high quality node representations in an unsupervised manner. This model first uses an extractor to preserve distinguishable features contained in original attributes, which are then fed to an aggregator to maintain the local relevance and global difference of nodes in encoding space. Finally, the strategy of deep graph infomax is applied to unify the global encoding rules. Experimental results demonstrate that the encoding performance of the model completely outperforms all mainstream comparative baselines on several classification benchmark datasets for transductive and inductive learning. [ABSTRACT FROM AUTHOR]

Research on sequence effects on learning visual categories has shown that interleaving (i.e., studying the categories in a mixed manner) facilitates category induction as compared to blocking (i.e., studying the categories one by one), but learners are unaware of the interleaving effect and prefer blocking. However, little attention has been paid to sequence effects in perceptual learning across further sensory modalities. The present (preregistered) research addresses this shortcoming by using auditory (birdcalls), olfactory (tealeaves), gustatory (ingredient mixtures), and tactile (stones) stimuli across four analog experiments. The number of participants per experiment was determined based on a medium effect size of interleaving. Participants studied six categories (with six exemplars, respectively) either interleaved or blocked. No single experiment showed a significant effect of interleaving. We ran a comprehensive meta‐analysis based on the data from all experiments, which revealed a significant small effect of interleaving, demonstrating its applicability to perceptual learning across all sensory modalities. Learners in the interleaved condition underestimated their classification performance. Overall, learners did not rate interleaving as less effective than blocking, which is at odds with previous studies that consistently demonstrated a metacognitive preference of blocking. Our findings suggest that learners rely less on conventional beliefs about the effectivity of study sequence when dealing with unfamiliar (blindfolded) perceptual learning tasks. [ABSTRACT FROM AUTHOR]

Firms currently operate in highly competitive scenarios, where the environmental conditions evolve over time. Many factors intervene simultaneously and their hard-to-interpret interactions throughout the supply chain greatly complicate decision-making. The complexity clearly manifests itself in the field of inventory management, in which determining the optimal replenishment rule often becomes an intractable problem. This paper applies machine learning to help managers understand these complex scenarios and better manage the inventory flow. Building on a dynamic framework, we employ an inductive learning algorithm for setting the most appropriate replenishment policy over time by reacting to the environmental changes. This approach proves to be effective in a three-echelon supply chain where the scenario is defined by seven variables (cost structure, demand variability, three lead times, and two partners' inventory policy). Considering four alternatives, the algorithm determines the best replenishment rule around 88% of the time. This leads to a noticeable reduction of operating costs against static alternatives. Interestingly, we observe that the nodes are much more sensitive to inventory decisions in the lower echelons than in the upper echelons of the supply chain. [ABSTRACT FROM AUTHOR]

This article introduces ILA4: A new algorithm designed to handle datasets with missing values. ILA4 is inspired by a series of ILA algorithms which also handle missing data with further enhancements. ILA4 is applied to datasets with varying completeness and also compared to other, known approaches for handling datasets with missing values. In the majority of cases, ILA4 produced favorable performance that is on a par with many established approaches for treating missing values including algorithms that are based on the Most Common Value (MCV), the Most Common Value Restricted to a Concept (MCVRC), and those that utilize the Delete strategy. ILA4 was also compared with three known algorithms namely: Logistic Regression, Naïve Bayes, and Random Forest; the accuracy obtained by ILA4 is comparable or better than the best results obtained from these three algorithms.

This paper presents an exploratory analysis of the implementation of Induction Helper, which is a learning aid created to facilitate and promote Thai students' inductive reasoning ability. Participants were three Thai lecturers of English writing and 45 Thai students. Data was collected through in-depth interviews, projective techniques, and observations of the online training cohorts. Results revealed four features of the Induction Helper that created drawbacks and need further improvement. These include its traditional format, lack of media richness, low interactivity, and inability to facilitate students' conceptualisation of the core principles of business writing. The study recommends modifications to improve these weak features. The results of the study indicate that the Induction Helper has inherent potential and can be upgraded to become a suitable learning resource for online learning. [ABSTRACT FROM AUTHOR]

Collaborative learning entails the involvement and the cooperation of a group of persons with the purpose of learning. Collaborative learning scripts aim to orchestrate the complex interaction among group members while Computer Supported Collaborative Learning scripts (CSCL scripts) is the research field in which IT techniques are involved in the management of the aspects of such an interaction. This article presents assessment-related aspects of an existing CSCL script authoring and deployment platform called COSTLyP. Assessment, nowadays, is considered as a vital constituent of CSCL scripts since it may affect some of their necessary components and mechanisms. The outcome of the implementation of an assessment plan may determine what should be the next step in a collaboration activity or what actions should be undertaken to bridge the gap between the expected results and the achieved level of knowledge or expertise. At the same time, assessment can also verify the regulation level that is required within each group; consequently, these scripts should be flexibly designed in order to adapt their evolution to the real needs of the participants. [ABSTRACT FROM AUTHOR]

Elasticity and Strength of Materials is an elementary discipline across many engineering degrees. Students perceive it as very difficult and abstract and students' active participation in the learning process is needed, due to its complexity and importance during the whole degree years. Hence, the main difficulty in teaching them is maintaining students' motivation and keeping their participation in the learning process. This is the reason to use new tools, such as problem-based learning (PBL) and flipped classroom, to help students understand and study the subject. In this work, we present the application of a problem-based learning to the lab in the Mechanical engineering degree, in of one the most time-consuming and difficult subjects of its program. Moreover, to enhance students' enthusiasm and motivation, these sessions included an innovative manufacturing technology, 3D printing, and digital image correlation (DIC). Before each practical session, the students are encouraged to watch an online video with the fundamental aspects. In order to assess the success of this laboratory course, after finishing the lab sessions, the students answered a non-formal quantitative survey. The results showed that the proposed project-based learning had the ability to help integrating the knowledge and improve the skills included in the main competences. Although these results are encouraging, there are still parts of the lab activity that should be improve in order to make the activity less time consuming and the most difficult part being easier for the students. [ABSTRACT FROM AUTHOR]

Graph representation learning has recently garnered significant attention due to its wide applications in graph analysis tasks. It is well-known that real-world networks are dynamic, with edges and nodes evolving over time. This presents unique challenges that are distinct from those of static networks. However, most graph representation learning methods are either designed for static graphs, or address only partial challenges associated with dynamic graphs. They overlook the intricate interplay between topology and temporality in the evolution of dynamic graphs and the complexity of sequence modeling. Therefore, we propose a new dynamic graph representation learning model, called as R-GraphSAGE, which takes comprehensive considerations for embedding dynamic graphs. By incorporating a recurrent structure into GraphSAGE, the proposed R-GraphSAGE explores structural and temporal patterns integrally to capture more fine-grained evolving patterns of dynamic graphs. Additionally, it offers a lightweight architecture to decrease the computational costs for handling snapshot sequences, achieving a balance between performance and complexity. Moreover, it can inductively process the addition of new nodes and adapt to the situations without labels and node attributes. The performance of the proposed R-GraphSAGE is evaluated across various downstream tasks with both synthetic and real-world networks. The experimental results demonstrate that it outperforms state-of-the-art baselines by a significant margin in most cases. • A recurrent graph neural network is proposed for dynamic graph embedding. • The R-GraphSAGE efficiently captures both topology and dynamics of temporal graphs. • The R-GraphSAGE inductively works for new nodes without labels and attributes. • The R-GraphSAGE shows strong competitiveness againt state-of-the-arts. [ABSTRACT FROM AUTHOR]

Unsupervised domain adaptation (UDA) is to learn classification models that make predictions for unlabeled data on a target domain, given labeled data on a source domain whose distribution diverges from the target one. Mainstream UDA methods strive to learn domain-aligned features such that classifiers trained on the source features can be readily applied to the target ones. Although impressive results have been achieved, these methods have a potential risk of damaging the intrinsic data structures of target discrimination, raising an issue of generalization particularly for UDA tasks in an inductive setting. To address this issue, we are motivated by a UDA assumption of structural similarity across domains, and propose to directly uncover the intrinsic target discrimination via constrained clustering, where we constrain the clustering solutions using structural source regularization that hinges on the very same assumption. Technically, we propose a hybrid model of Structurally Regularized Deep Clustering, which integrates the regularized discriminative clustering of target data with a generative one, and we thus term our method as H-SRDC. Our hybrid model is based on a deep clustering framework that minimizes the Kullback-Leibler divergence between the distribution of network prediction and an auxiliary one, where we impose structural regularization by learning domain-shared classifier and cluster centroids. By enriching the structural similarity assumption, we are able to extend H-SRDC for a pixel-level UDA task of semantic segmentation. We conduct extensive experiments on seven UDA benchmarks of image classification and semantic segmentation. With no explicit feature alignment, our proposed H-SRDC outperforms all the existing methods under both the inductive and transductive settings. We make our implementation codes publicly available at https://github.com/huitangtang/H-SRDC. [ABSTRACT FROM AUTHOR]

Observing category exemplars in an interleaved manner is more beneficial for inductive learning than blocked (massed) presentation, a phenomenon termed the interleaving effect on inductive learning. However, people tend to erroneously believe that massed is more beneficial than interleaved learning, and learners prefer the former during self-regulated learning. We report four experiments designed to investigate whether explicit instructions, which include individual performance feedback and the interleaving effect results from previous research, can (1) correct metacognitive illusions regarding the interleaving effect, (2) promote self-employment of interleaving, and (3) facilitate category learning. In addition, the current study explored (4) whether the intervention effect is long-lasting and (5) transferable to learning of categories in other domains. Experiments 1–4 established the effectiveness of the instruction intervention to enhance metacognitive appreciation of the interleaving effect, to promote self-employment of interleaving, and to facilitate learning of new categories. The intervention effect was long-lasting (at least 24 h; Experiment 2), and transferable to learning of categories in different domains (Experiments 3 and 4). These findings support the practical use of the instruction intervention. [ABSTRACT FROM AUTHOR]

This article introduces ILA4: A new algorithm designed to handle datasets with missing values. ILA4 is inspired by a series of ILA algorithms which also handle missing data with further enhancements. ILA4 is applied to datasets with varying completeness and also compared to other, known approaches for handling datasets with missing values. In the majority of cases, ILA4 produced favorable performance that is on a par with many established approaches for treating missing values including algorithms that are based on the Most Common Value (MCV), the Most Common Value Restricted to a Concept (MCVRC), and those that utilize the Delete strategy. ILA4 was also compared with three known algorithms namely: Logistic Regression, Naïve Bayes, and Random Forest; the accuracy obtained by ILA4 is comparable or better than the best results obtained from these three algorithms. [ABSTRACT FROM AUTHOR]

Mechanical Design is a subject usually included in Chemical Engineering Degrees. In this work, we present the application of a project-based learning to the lab in two different engineering degrees, in of one the most time-consuming and difficult subjects of their programs. These two degrees, Mechanical and Chemical engineering degrees, were selected in order to compare the learning outcomes and satisfaction with the activity in the degree more related to mechanical concepts and the Chemical engineering degree. Moreover, to enhance students' enthusiasm and motivation, these sessions included an innovative manufacturing technology, 3D printing, and digital image correlation (DIC). Before each practical session, the students are encouraged to watch an online video with the fundamental aspects. In order to assess the success of this methodology, after finishing the lab sessions, the students answered a non-formal quantitative survey. The results showed that the proposed project-based learning had the ability to help integrating the knowledge and improve the skills included in the main competences. Although these results are encouraging, there are still parts of the lab activity that should be improve in order to make the activity less time consuming and the most difficult part being easier for the students. • A mechanical laboratory approach for chemical engineers was successfully applied. • The design and assessment of a project-based learning lab is discussed in detail. • Project-based learning, flipped classroom and collaborative learning was combined. • The employment of this new laboratory achieves high student satisfaction. [ABSTRACT FROM AUTHOR]

The performance of optimization algorithms, and consequently of AI/machine learning solutions, is strongly influenced by the setting of their hyperparameters. Over the last decades, a rich literature has developed proposing methods to automatically determine the parameter setting for a problem of interest, aiming at either robust or instance-specific settings. Robust setting optimization is already a mature area of research, while instance-level setting is still in its infancy, with contributions mainly dealing with algorithm selection. The work reported in this paper belongs to the latter category, exploiting the learning and generalization capabilities of artificial neural networks to adapt a general setting generated by state-of-the-art automatic configurators. Our approach differs significantly from analogous ones in the literature, both because we rely on neural systems to suggest the settings, and because we propose a novel learning scheme in which different outputs are proposed for each input, in order to support generalization from examples. The approach was validated on two different algorithms that optimized instances of two different problems. We used an algorithm that is very sensitive to parameter settings, applied to generalized assignment problem instances, and a robust tabu search that is purportedly little sensitive to its settings, applied to quadratic assignment problem instances. The computational results in both cases attest to the effectiveness of the approach, especially when applied to instances that are structurally very different from those previously encountered.