Multiple Graphs and Low-Rank Embedding for Multi-Source Heterogeneous Domain Adaptation

Multi-source domain adaptation is a challenging topic in transfer learning, especially when the data of each domain are represented by different kinds of features, i.e., Multi-source Heterogeneous Domain Adaptation (MHDA). It is important to take advantage of the knowledge extracted from multiple sources as well as bridge the heterogeneous spaces for handling the MHDA paradigm. This article proposes a novel method named Multiple Graphs and Low-rank Embedding (MGLE), which models the local structure information of multiple domains using multiple graphs and learns the low-rank embedding of the target domain. Then, MGLE augments the learned embedding with the original target data. Specifically, we introduce the modules of both domain discrepancy and domain relevance into the multiple graphs and low-rank embedding learning procedure. Subsequently, we develop an iterative optimization algorithm to solve the resulting problem. We evaluate the effectiveness of the proposed method on several real-world datasets. Promising results show that the performance of MGLE is better than that of the baseline methods in terms of several metrics, such as AUC, MAE, accuracy, precision, F1 score, and MCC, demonstrating the effectiveness of the proposed method.

Mixed Information Flow for Cross-Domain Sequential Recommendations

Cross-domain sequential recommendation is the task of predict the next item that the user is most likely to interact with based on past sequential behavior from multiple domains. One of the key challenges in cross-domain sequential recommendation is to grasp and transfer the flow of information from multiple domains so as to promote recommendations in all domains. Previous studies have investigated the flow of behavioral information by exploring the connection between items from different domains. The flow of knowledge (i.e., the connection between knowledge from different domains) has so far been neglected. In this article, we propose a mixed information flow network for cross-domain sequential recommendation to consider both the flow of behavioral information and the flow of knowledge by incorporating a behavior transfer unit and a knowledge transfer unit . The proposed mixed information flow network is able to decide when cross-domain information should be used and, if so, which cross-domain information should be used to enrich the sequence representation according to users’ current preferences. Extensive experiments conducted on four e-commerce datasets demonstrate that the proposed mixed information flow network is able to improve recommendation performance in different domains by modeling mixed information flow. In this article, we focus on the application of mixed information flow network s to a scenario with two domains, but the method can easily be extended to multiple domains.

Kindergarten teachers' evaluation: perceptions of the new Israeli multiple domains performance tool

Purpose In 2012, the Israeli Ministry of Education and its Testing and Evaluation Department introduced a new tool to evaluate the quality of kindergarten teachers’ work. This paper aims to identify how kindergarten teachers perceive the new multiple domains performance tool. Design/methodology/approach The study applied a qualitative paradigm of data collection and analysis. Data collection consisted of semi-structured in-depth interviews conducted with 36 kindergarten teachers. Findings Findings indicated that most kindergarten teachers perceive their work plan and the kindergarten climate as the most important evaluation domains, while perceiving involving parents as the least important and even an unnecessary domain. One-third of them indicated that an innovation domain should be added. Also, the kindergarten teachers perceived the use of the KT-MDPT as both positive and negative. Originality/value There is a clear dearth in scholarly literature dealing with the evaluation of the quality of kindergarten teachers’ work. This study is the first to reveal Israeli kindergarten teachers' attitudes regarding this new tool for work quality evaluation.

Multi-Source and Multi-Representation Adaptation for Cross-Domain Electroencephalography Emotion Recognition

Due to the non-invasiveness and high precision of electroencephalography (EEG), the combination of EEG and artificial intelligence (AI) is often used for emotion recognition. However, the internal differences in EEG data have become an obstacle to classification accuracy. To solve this problem, considering labeled data from similar nature but different domains, domain adaptation usually provides an attractive option. Most of the existing researches aggregate the EEG data from different subjects and sessions as a source domain, which ignores the assumption that the source has a certain marginal distribution. Moreover, existing methods often only align the representation distributions extracted from a single structure, and may only contain partial information. Therefore, we propose the multi-source and multi-representation adaptation (MSMRA) for cross-domain EEG emotion recognition, which divides the EEG data from different subjects and sessions into multiple domains and aligns the distribution of multiple representations extracted from a hybrid structure. Two datasets, i.e., SEED and SEED IV, are used to validate the proposed method in cross-session and cross-subject transfer scenarios, experimental results demonstrate the superior performance of our model to state-of-the-art models in most settings.

A connectivity-constrained computational account of topographic organization in primate high-level visual cortex

Inferotemporal (IT) cortex in humans and other primates is topographically organized, containing multiple hierarchically organized areas selective for particular domains, such as faces and scenes. This organization is commonly viewed in terms of evolved domain-specific visual mechanisms. Here, we develop an alternative, domain-general and developmental account of IT cortical organization. The account is instantiated in interactive topographic networks (ITNs), a class of computational models in which a hierarchy of model IT areas, subject to biologically plausible connectivity-based constraints, learns high-level visual representations optimized for multiple domains. We find that minimizing a wiring cost on spatially organized feedforward and lateral connections, alongside realistic constraints on the sign of neuronal connectivity within model IT, results in a hierarchical, topographic organization. This organization replicates a number of key properties of primate IT cortex, including the presence of domain-selective spatial clusters preferentially involved in the representation of faces, objects, and scenes; columnar responses across separate excitatory and inhibitory units; and generic spatial organization whereby the response correlation of pairs of units falls off with their distance. We thus argue that topographic domain selectivity is an emergent property of a visual system optimized to maximize behavioral performance under generic connectivity-based constraints.

BlockREV: Blockchain-Enabled Multi-Controller Rule Enforcement Verification in SDN

Compared with the classical structure with only one controller in software-defined networking (SDN), multi-controller topology structure in SDN provides a new type of cross-domain forwarding network architecture with multiple centralized controllers and distributed forwarding devices. However, when the network includes multiple domains, lack of trust among the controllers remains a challenge how to verify the correctness of cross-domain forwarding behaviors in different domains. In this paper, we propose a novel secure multi-controller rule enforcement verification (BlockREV) mechanism in SDN to guarantee the correctness of cross-domain forwarding. We first adopt blockchain technology to provide the immutability and privacy protection for forwarding behaviors. Furthermore, we present an address-based aggregate signature scheme with appropriate cryptographic primitives, which is provably secure in the random oracle model. Moreover, we design a verification algorithm based on hash values of forwarding paths to check the consistency of forwarding order. Finally, experimental results demonstrate that the proposed BlockREV mechanism is effective and suitable for multi-controller scenarios in SDN.

Social hierarchies and social networks in humans

Across species, social hierarchies are often governed by dominance relations. In humans, where there are multiple culturally valued axes of distinction, social hierarchies can take a variety of forms and need not rest on dominance relations. Consequently, humans navigate multiple domains of status, i.e. relative standing. Importantly, while these hierarchies may be constructed from dyadic interactions, they are often more fundamentally guided by subjective peer evaluations and group perceptions. Researchers have typically focused on the distinct elements that shape individuals’ relative standing, with some emphasizing individual-level attributes and others outlining emergent macro-level structural outcomes. Here, we synthesize work across the social sciences to suggest that the dynamic interplay between individual-level and meso-level properties of the social networks in which individuals are embedded are crucial for understanding the diverse processes of status differentiation across groups. More specifically, we observe that humans not only navigate multiple social hierarchies at any given time but also simultaneously operate within multiple, overlapping social networks. There are important dynamic feedbacks between social hierarchies and the characteristics of social networks, as the types of social relationships, their structural properties, and the relative position of individuals within them both influence and are influenced by status differentiation. This article is part of the theme issue ‘The centennial of the pecking order: current state and future prospects for the study of dominance hierarchies’.

Hybrid and Virtual Educational Simulation Games (vESGs) for the Remote Learning Era

Virtual educational simulation games (vESGs) promote unique combinations of learning interactions and affordances to create environments with which students can engage to effectively learn about complex phenomena and processes in multiple domains. Using the GlobalEd vESG as an example case throughout the chapter, the authors discuss (1) the key functions and experiences that vESGs provide to learners; (2) the types of valuable student interactions that can be expected when playing a vESG and strategies for maximizing these interactions for learning; (3) strategies for teacher implementation and adaptation of vESGs, as well as professional development programs to support their use of vESGs in classrooms; and (4) observed benefits of using vESGs as evidenced from over a decade of implementation of the GlobalEd vESG in authentic classroom settings.