Knowledge Transfer Strategies Research Articles

Research and Model Library Construction in Teacher-Student Learning Architectures for Knowledge Transfer

This paper summarizes and replicates multiple classical and cutting-edge knowledge transfer methods, including Factor Transfer (FT), Knowledge Distillation (KD), Deep Mutual Learning (DML), Contrastive Representation Distillation (CRD), and Born-Again Self-Distillation (BSS). Additionally, we studied three advanced knowledge transfer methods: Relational Knowledge Distillation (RKD), Similarity-Preserving (SP), and Attention-based Feature Distillation (AFD), successfully replicating an optimized version of KD, namely RKD. Based on these methods, a flexible model library was constructed in Pycharm, allowing the quick integration of multiple knowledge transfer strategies. The experimental results are visualized through a user-friendly interface, enabling intuitive comparisons of model training speed and performance across different methods. This research provides valuable insights into the challenge of building a reusable framework that efficiently integrates various knowledge transfer strategies into deep neural networks.

Self-improved multi-view interactive knowledge transfer

Multi-view learning (MVL) is a promising data fusion technique based on the principles of consensus and complementarity. Despite significant advancements in this field, several challenges persist. First, scalability remains an issue, as many existing approaches are limited to two-view scenarios, making them difficult to extend to more complex multi-view settings. Second, implementing consensus principles in current techniques often requires adding extra terms to the model’s objective function or constraints, leading to increased complexity. Additionally, when applying complementarity principles, most studies focus on pairwise interactions between views, overlooking the benefits of deeper and broader multi-view interactions. To address these challenges, this paper proposes the multi-view interactive knowledge transfer (MVIKT) model, which enhances scalability by effectively managing interactions across multiple views, thereby overcoming the limitations of traditional two-view models. More importantly, MVIKT introduces a novel interactive knowledge transfer strategy that simplifies the application of the consensus principle by eliminating the need for additional terms. By treating margin distances as transferable knowledge and facilitating multiple rounds of interaction, MVIKT uncovers deeper complementary information, thereby improving the overall effectiveness of MVL. Theoretical analysis further supports the MVIKT model, demonstrating that transferring knowledge through margin distance is capable of lowering the upper bound of the generalization error. Extensive experiments across diverse datasets validate MVIKT’s superiority, showing statistically significant improvements over benchmark methods.

Jains in Switzerland

Abstract There are 120 Jains living in Switzerland today. Desiring to exchange information about their religion and to expand their knowledge, they started to meet in 2008. This initiated a community-building process in which Jains of different branches took part. Such a process, as well as the diaspora situation itself, is always connected with negotiations and religious transformations, which is also evident in the Swiss context. Following the common meetings, a distinct form of Jainism was created in Switzerland. This new form is supradenominational and universal and based on aspects such as vegetarianism, environmentalism, and nonviolence. Additionally, the Swiss Jains developed new strategies of knowledge transfer. This article focuses on not only the formation of a Swiss Jain community but also its dissolution as no common gatherings have taken place since 2016. Therefore, factors are named that can lead to the dissolution of a community.

Flood inundation monitoring using multi-source satellite imagery: a knowledge transfer strategy for heterogeneous image change detection

Flood emergency mapping is essential for flood management, often requiring near real-time extraction of large-scale flood extents by combining pre- and post-event multi-source remote sensing images. Pre-event optical imagery delineates the normal water extent, providing a benchmark for estimation of post-flood changes. Synthetic aperture radar (SAR) imagery provides rapid and accurate interpretation of flood inundation extent during the rainy period. Post-classification comparison is one of the fundamental methods for flood mapping of multi-source imagery, as the image characteristics of SAR and optical imagery are inherently different. However, the accuracy of flood mapping depends on the accuracy of water body delineation from single temporal imagery, which can lead to error propagation in flood extent determination. Change detection methods can extract flood extent directly from pre- and post-event imagery, but the models need to learn a consistent flood feature description between optical and SAR imagery from a limited flood dataset. Here, we propose an automatic method for flood inundation extent extraction using pre- and post-event multi-source imagery that requires only a small number of pseudo-change labels. The methodology adopts a pseudo-Siamese network framework as a Heterogeneous - Flood Inundation Extraction Network (H-FIENet), to detect flood extent between the pre‐ and post-event heterogeneous images. Spatially inconsistent multi-source pre- and post-event imagery was used to create a pseudo flood dataset, and this dataset was used to transfer water body feature knowledge from the pre-trained model to the flood extraction model using a cross-task knowledge transfer strategy. Pre- and post-event images from different satellite sources and different flood scenarios were used to evaluate the performance of H-FIENet. We found that: (1) The methodology produced an overall accuracy of over 0.94 for flood inundation extraction from multi-source heterogeneous pre- and post-event imagery. (2) H-FIENet can detect both expansion and recession of the flood extent using any dual-temporal imagery. Our work makes it possible to automate time-series flood monitoring from multi-source remote sensing imagery.

Unlocking the Power of Cascading Teaching: A Key Strategy for Effective Knowledge Transfer and Professional Development

"Unlocking the Power of Cascading Teaching: A Key Strategy for Effective Knowledge Transfer and Professional Development discusses the importance of cascading teaching as a strategy for transferring knowledge and promoting professional development. The paper highlights the benefits of cascading teaching, such as increased engagement, improved retention of information, and enhanced collaboration among colleagues. It is found that cascading teaching is likely a research paper, article, or book that discusses the concept of cascading teaching as a strategy for knowledge transfer and professional development. It may explore how cascading teaching can be used to effectively share knowledge and skills within an organization or educational setting. The abstract also emphasizes the role of leadership in supporting and facilitating cascading teaching initiatives within organizations. Overall, the abstract underscores the value of cascading teaching as a powerful tool for enhancing learning and development in the workplace.

A Multiform Optimization Framework for Multiobjective Feature Selection in Classification

Feature selection in machine learning as a key data processing technique has two conflicting goals: minimizing the classification error rate and minimizing the number of features selected. However, most of the existing multi-objective feature selection methods face the problems of easily falling into local optima and slow convergence by virtue of their problem characteristics, such as partially conflicting objectives and highly discontinuous Pareto fronts. To solve these problems, this article proposes a multiform optimization framework to solve a multi-objective feature selection task together with several auxiliary single-objective feature selection tasks in a multitask environment. The proposed framework uses the problem-solving experience of single-objective tasks to assist the multi-objective feature selection task in exploring more promising regions and accelerating the convergence speed. Specifically, a knowledge transfer strategy based on the search experience of different tasks is developed to accomplish multiform optimization. In addition, a diversity enhancement mechanism is presented to improve search ability in promising decision space areas by considering historical information about the population. In most cases, the experiment results on 27 datasets demonstrate that the proposed technique can uncover more diversified feature subsets on the Pareto front in less time than existing state-of-the-art methods.

Advancing 3D point cloud understanding through deep transfer learning: A comprehensive survey

The 3D point cloud (3DPC) has significantly evolved and benefited from the advances of deep learning (DL). However, the latter faces various issues, including the lack of data or annotated data, the existence of a significant gap between training data and test data, and the requirement for high computational resources. To that end, deep transfer learning (DTL), which decreases dependency and costs by utilizing knowledge gained from a source data/task in training a target data/task, has been widely investigated. Numerous DTL frameworks have been suggested for aligning point clouds obtained from several scans of the same scene. Additionally, DA, which is a subset of DTL, has been modified to enhance the point cloud data’s quality by dealing with noise and missing points. Ultimately, fine-tuning and DA approaches have demonstrated their effectiveness in addressing the distinct difficulties inherent in point cloud data. This paper presents the first review shedding light on this aspect. it provides a comprehensive overview of the latest techniques for understanding 3DPC using DTL and domain adaptation (DA). Accordingly, DTL’s background is first presented along with the datasets and evaluation metrics. A well-defined taxonomy is introduced, and detailed comparisons are presented, considering different aspects such as different knowledge transfer strategies, and performance. The paper covers various applications, such as 3DPC object detection, semantic labeling, segmentation, classification, registration, downsampling/upsampling, and denoising. Furthermore, the article discusses the advantages and limitations of the presented frameworks, identifies open challenges, and suggests potential research directions.

A multi-task evolutionary algorithm for solving the problem of transfer targets

In recent years, multi-task optimisation, aimed at handling multiple optimisation problems simultaneously, has received great attention in the field of evolutionary algorithms. Research on multi-task evolutionary algorithms mostly focuses on solving the problem of effective transfer, which usually transfers the extracted effective knowledge to the matching selection stage or environment selection stage. However, the impact of these transfer targets on algorithm performance is rarely studied. To solve the problem of transfer targets, we propose a multi-task evolutionary algorithm with a hybrid knowledge transfer strategy (MTEA-HKTS). Firstly, we determined three transfer targets and designed knowledge transfer strategies for each stage by analysing the population changes in the differential evolution algorithm. Secondly, a knowledge transfer strategy is devised to control the transfer targets. Finally, we designed a new archive update strategy that uses a distribution model constructed for recent generations of populations to calculate gene similarity. The experimental results on the multi-task benchmark problems show that the transfer targets affect the performance of the multi-task optimisation algorithm, and verify the superiority of the proposed MTEA-HKTS algorithm.

A Hybrid Preference Interaction Mechanism for Multi-Satellite Imaging Dynamic Mission Planning

The existing multi-satellite dynamic mission planning system hardly satisfies the requirements of fast response time and high mission benefit in highly dynamic situations. In the meantime, a reasonable decision-maker preference mechanism is an additional challenge for multi-satellite imaging dynamic mission planning based on user preferences (MSDMPUP). Therefore, this study proposes the hybrid preference interaction mechanism and knowledge transfer strategy for the multi-objective evolutionary algorithm (HPIM–KTSMOEA). Firstly, an MSDMPUP model based on a task rolling window is constructed to achieve timely updating of the target task importance degree through the simultaneous application of periodic triggering and event triggering methods. Secondly, the hybrid preference interaction mechanism is constructed to plan according to the satellite controller’s preference-based commands in different phases of the optimal search of the mission planning scheme to effectively respond to the dynamic changes in the environment. Finally, a knowledge transfer strategy for the multi-objective evolutionary algorithm is proposed to accelerate population convergence in new environments based on knowledge transfer according to environmental variability. Simulation experiments verify the effectiveness and stability of the method in processing MSDMPUP. This study found that the HPIM–KTSMOEA algorithm has high task benefit, short response time, and high task completion when processing MSDMPUP.

KNOWLEDGE TRANSFER PRACTICES AND STRATEGIES IN HIGHER EDUCATION

This study aims to investigate knowledge transfer practices and strategies measured by knowledge vision, leadership, sharing culture, strategies, and IT infrastructures. It also examines how the variables affect organizational performance. By involving 118 respondents collected through an online survey and analyzed using descriptive statistics and multiple linear regression, the study found that knowledge-sharing and IT infrastructure significantly influence organizational performance, while knowledge vision, knowledge leadership, and knowledge-sharing culture do not significantly affect organizational performance. Practices such as public lectures, seminars, workshops, collegial interchange, internships, and research collaborations are considered effective in supporting knowledge transfer activities in higher education. In addition, the knowledge creation process through socialization, externalization, combination, and internalization, and factors such as vision, leadership, culture, and IT infrastructure must be managed properly to support the knowledge transfer process and formulate appropriate strategies.

A multi-population evolutionary algorithm based on knowledge transfer for constrained many-objective optimization

ABSTRACT Constrained Many-objective Optimization Problems (CMaOPs) are challenging in handling objectives and constraints simultaneously. Here, a novel Constrained Many-objective Optimization Evolutionary Algorithm (CMaOEA) based on Multi-population, Knowledge transfer and Improved environmental selection called CMaMKI is proposed to handle CMaOPs. The proposed framework evolves a task population to solve the original CMaOP and evolves another population to solve a helper problem derived from the original one. To assist solving the original CMaOP, a knowledge expression and transfer strategy is designed to share useful information in the helper population with the task population. Meanwhile, to balance population convergence, diversity and feasibility, an enhanced environmental selection strategy is devised by combining the ε-constrained technique, θ-dominance and subregional density evaluation. The proposed algorithm is evaluated and contrasted with six state-of-the-art algorithms on a set of benchmark CMaOPs. The experimental results demonstrate the superiority and competitiveness of the proposed method.

Knowledge Transfer of Site Based Construction Management Team of ABC Company: Basis for the Development of Knowledge Transfer Plan

The study determines the readiness of ABC Company and the status of the project site based construction management team (CMT) on knowledge transfer (KT) as basis for the development of the proposed knowledge transfer plan (KTP). Descriptive method was used to obtain information on the levels of readiness on organizational characteristics and resources requirement of ABC Company and on the gaps in terms of idea creation, sharing, dissemination, evaluation and adoption in the project site based CMT. Descriptive statistics was used to present the data on readiness; anything below 100% in terms of idea creation, sharing, dissemination, evaluation and adoption was considered a gap. The study revealed that ABC Company has a moderately ready status on its readiness. Improvement was needed on KT strategy, rewards systems, knowledge hoarding, knowledge required, budget, and even on the core and support team that was essential in the development of the proposed KTP. The project site based CMT had gaps to be attended to on idea creation, sharing and dissemination. Those gaps were considered valuable input in the development of the proposed KTP. The development of the proposed KTP was grounded on quality management system that considered the readiness of ABC Company and the gaps found in the project site based CMT as inputs. The proposed KTP composed of four stages, namely, Management Responsibility, Resource Management, Knowledge Transfer Realization and Measurement, Analysis and Improvement. Intervention strategies presented in the KTP would address the particular area determined to be either absent or not consistently implemented with feed forward and feedback for continual improvement.

Knowledge transfer and protection in international joint ventures: An integrative review

Cross-border transfer and the protection of knowledge are important for multinational enterprises (MNEs) to develop their network partners’ capabilities while simultaneously safeguarding competitive advantages. However, they can be challenging for MNEs due to cultural and institutional differences between home and host markets. This poses a dilemma for MNEs, which is how to strike a balance between their knowledge transfer (KT) and knowledge protection (KP) strategies. It is notable that, so far, research has primarily investigated these two areas independently, lacking an integrative view. Therefore, in this article, we reviewed 98 academic articles exploring knowledge transfer/protection in MNEs operating under international joint venture (IJV) arrangements and assessed publications from the last two decades (2000–2022). Drawing from institutional theory and the bargaining power perspective, we developed a conceptual framework highlighting the external and internal factors influencing KT and KP. Subsequently, we contextualized these factors within the specific domain of IJVs, drawing on insights gleaned from the studies in our sample. The interplay of these factors, along with their contextual nuances, provides a holistic and in-depth understanding of how knowledge is managed within the complex dynamics of IJVs. In addition, our review contributes to our understanding of knowledge management in MNEs by identifying novel gaps in the literature and suggesting a number of avenues for future research.

Trend of Knowledge Transfer Strategy in the Libraries: A Bibliometrics Analysis

Trend of Knowledge Transfer Strategy in the Libraries: A Bibliometrics Analysis

An Efficient Knowledge Transfer Strategy for Spiking Neural Networks from Static to Event Domain

Spiking neural networks (SNNs) are rich in spatio-temporal dynamics and are suitable for processing event-based neuromorphic data. However, event-based datasets are usually less annotated than static datasets. This small data scale makes SNNs prone to overfitting and limits their performance. In order to improve the generalization ability of SNNs on event-based datasets, we use static images to assist SNN training on event data. In this paper, we first discuss the domain mismatch problem encountered when directly transferring networks trained on static datasets to event data. We argue that the inconsistency of feature distributions becomes a major factor hindering the effective transfer of knowledge from static images to event data. To address this problem, we propose solutions in terms of two aspects: feature distribution and training strategy. Firstly, we propose a knowledge transfer loss, which consists of domain alignment loss and spatio-temporal regularization. The domain alignment loss learns domain-invariant spatial features by reducing the marginal distribution distance between the static image and the event data. Spatio-temporal regularization provides dynamically learnable coefficients for domain alignment loss by using the output features of the event data at each time step as a regularization term. In addition, we propose a sliding training strategy, which gradually replaces static image inputs probabilistically with event data, resulting in a smoother and more stable training for the network. We validate our method on neuromorphic datasets, including N-Caltech101, CEP-DVS, and N-Omniglot. The experimental results show that our proposed method achieves better performance on all datasets compared to the current state-of-the-art methods. Code is available at https://github.com/Brain-Cog-Lab/Transfer-for-DVS.

Transnational networks of human resources and knowledge in East Asia: a case study of Taiwan merchant Wang Xuenong (1870–1915) and his trading company

Abstract Taiwan is an island and trade has always been the locomotive of its economic development. From the 1620s to the 1960s, cane sugar was Taiwan's most representative export commodity. Yet little attention has been paid to the business strategies of sugar traders and the changes in their thinking. How did the Takow (Kaohsiung) merchants who first went to Japan and Hong Kong to conduct cross-border trade in person learn about international trade and build a network of human resources that crossed borders, especially after the 1870s? And how did they face the great changes of an era in which tradition and modernity were intertwined, so that, following the regime transfer in the 1890s from the Qing Dynasty to the Japanese empire, they were able to expand their business territory and become major sugar merchants in southern Taiwan? This article examines the career of Wang Xuenong—a well-known sugar merchant in Taiwan during the Meiji period (1868–1912). It attempts to explain, from the perspective of cross-cultural knowledge transfer and human resource strategies, why and how sugar merchants such as Wang, who had gone to Japan in the early years of the Meiji Restoration for purposes of cross-border trade, introduced a trading company system that incorporated a mixture of East Asian and Western elements. It further investigates how they expanded their business from the sugar trade into a wider commercial domain that included mechanical rice milling and steamship transport. Finally, it looks at how their actions affected a transformation of Taiwan's commercial culture from the late Qing Dynasty to the early days of Japanese rule, and the historical significance of these changes in Taiwan's transitions towards industrialisation and modernisation.

Knowledge investment and search for innovation: evidence from the UK firms

Recent research on innovation management and knowledge transfer has demonstrated that industry knowledge collaboration and knowledge spillovers matter for innovation, but so does a firm's Research and Development (R&D). Conditional to a firm's R&D investment, this study makes a theoretical investigation into the role of two knowledge transfer strategies—industry coopetition and industry knowledge spillovers for a firm's innovation. Based on an analysis of a sample of 17,859 UK firms from 2002 to 2014, we demonstrated why and under what conditions firms will (a) invest in internal R&D, (b) engage in coopetition, and (c) access knowledge spillovers to introduce new to firm (incremental innovation) and new to market products (radical innovation). The results of this study demonstrate that firm managers who choose knowledge spillovers versus coopetition are likely to achieve radical vis-à-vis incremental innovation. Benefits from the coopetition can be achieved with low investment in R&D, while R&D is essential in recognizing the knowledge spillover for radical innovation. By deciding whether to deploy its costly R&D and access external knowledge via industry coopetition or spillovers, the firm is also making a concomitant decision about the type of innovative activity it will generate. Thus, a firm strategy for knowledge transfer and investing in knowledge internally is inextricably linked to a firm strategy involving the type of innovative output.

Diversified Knowledge Transfer Strategy for Multitasking Particle Swarm Optimization.

Evolutionary multitasking optimization (EMTO) has capability of performing a population of individuals together by sharing their intrinsic knowledge. However, the existed methods of EMTO mainly focus on improving its convergence using parallelism knowledge belonging to different tasks. This fact may lead to the problem of local optimization in EMTO due to unexploited knowledge on behalf of the diversity. To address this problem, in this article, a diversified knowledge transfer strategy is proposed for multitasking particle swarm optimization algorithm (DKT-MTPSO). First, according to the state of population evolution, an adaptive task selection mechanism is introduced to manage the source tasks that contribute to the target tasks. Second, a diversified knowledge reasoning strategy is designed to capture the knowledge of convergence, as well as the knowledge associated with diversity. Third, a diversified knowledge transfer method is developed to expand the region of generated solutions guided by acquired knowledge with different transfer patterns so that the search space of tasks can be explored comprehensively, which is favor of EMTO alleviating local optimization. Finally, the performance of the proposed algorithm is evaluated in comparison with some other state-of-the-art EMTO algorithms on multiobjective multitasking benchmark test suits, and the practicality of the algorithm is verified in a real-world application study. The results of experiments demonstrate the superiority of DKT-MTPSO compared to other algorithms.

Evolutionary Multiform Optimization With Two-Stage Bidirectional Knowledge Transfer Strategy for Point Cloud Registration

Point cloud registration is an important task in computer vision, where the goal is to estimate a transformation to align a pair of point clouds. Most of the existing registration methods face the problems of poor robustness and getting stuck in local optima. Evolutionary multitasking is an effective paradigm to enhance global search capability and improve convergence characteristics through knowledge transfer across multiple related tasks. Inspired by evolutionary multitasking, this paper proposes a multiform optimization approach through evolutionary multitasking for solving the point cloud registration problems. we first construct two related registration tasks with different functional landscapes to form a multiform optimization problem. Compared with methods that only focus on a single registration attribute, the two proposed tasks focus on robustness and precision of registration, respectively. Then, a new two-stage bidirectional knowledge transfer strategy is presented, which can implement efficient knowledge transfer among two related tasks. Finally, both simulations and real experiments show the power of our method. The proposed method is robust to noise, outliers, and partial overlaps, and is effective in multiple real registration scenarios, such as object registration, scene reconstruction, simultaneous localization and mapping.

Higher Order Knowledge Transfer for Dynamic Community Detection With Great Changes

Network structure evolves with time in the real world, and the discovery of changing communities in dynamic networks is an important research topic that poses challenging tasks. Most existing methods assume that no significant change occurs; namely, the difference between adjacent snapshots is slight. However, great change exists in the real world usually. The great change in the network will result in the community detection algorithms are difficulty obtaining valuable information from the previous snapshot, leading to negative transfer for the next time steps. This paper focuses on dynamic community detection with substantial changes by integrating higher-order knowledge from the previous snapshots to aid the subsequent snapshots. Moreover, to improve search efficiency, a higher-order knowledge transfer strategy is designed to determine first-order and higher-order knowledge by detecting the similarity of the adjacency matrix of snapshots. In this way, our proposal can keep the advantages of previous community detection results and transfer them to the next task. We conduct the experiments on four real-world networks, including the networks with great or minor changes. Experimental results in the low-similarity datasets demonstrate that higher-order knowledge is more valuable than first-order knowledge when the network changes significantly and keeps the advantage even if handling the high-similarity datasets. Our proposal can also guide other dynamic optimization problems with great changes.