報告一：A Development of Interpretable Rule-Based Architecture Under Privacy Constraints: A Framework of Granular Computing
報告人： Prof. Witold Pedrycz（Information Science主編）
摘要：In data analytics, system modeling, and decision-making models, the aspects of interpretability and explainability are of paramount relevance as emphasized in studies on explainable Artificial Intelligence (XAI). Those requirements are especially timely when the design of models has to be realized when considering strict requirements of privacy and security. We advocate that to efficiently address these challenges, it becomes beneficial to engage the fundamental framework of Granular Computing. It is demonstrated that a conceptualization of information granules can be conveniently carried out with the use of information granules (for example, fuzzy sets, sets, rough sets, and alike). We present a comprehensive discussion of information granules-oriented design of rule-based architectures and their interpretation by engaging an innovative mechanism of federated unsupervised learning using which information granules are constructed.
報告二：Objective-Domain Dual Decomposition: An Effective Approach to Optimizing Partially Differentiable Objective Functions
報告人：張曉明教授（IEEE Fellow） 單位：香港浸會大學
摘要：This paper addresses a class of optimization problems in which either part of the objective function is differentiable while the rest is nondifferentiable or the objective function is differentiable in only part of the domain. Accordingly, we propose a dual-decomposition-based approach that includes both objective decomposition and domain decomposition. In the former, the original objective function is decomposed into several relatively simple subobjectives to isolate the nondifferentiable part of the objective function, and the problem is consequently formulated as a multiobjective optimization problem (MOP). In the latter decomposition, we decompose the domain into two subdomains, that is, the differentiable and nondifferentiable domains, to isolate the nondifferentiable domain of the nondifferentiable subobjective. Subsequently, the problem can be optimized with different schemes in the different subdomains. We propose a population-based optimization algorithm, called the simulated water-stream algorithm (SWA), for solving this MOP. The SWA is inspired by the natural phenomenon of water streams moving toward a basin, which is analogous to the process of searching for the minimal solutions of an optimization problem. The proposed SWA combines the deterministic search and heuristic search in a single framework. Experiments show that the SWA yields promising results compared with its existing counterparts.
報告三：Evolutionary Mult-objective and Many-objective Optimization Algorithm Using Region Decomposition
報告四：Design Automation of Intelligent Robotic Systems Based on Evolutionary Computation
摘要：The main reason why the performance of domestic robots is generally difficult to reach the same level of that of foreign countries mainly lies in the lack of systematic continuous optimization and design automation. How to form a framework of design automation of intelligent robotic systems is the main topic of this report. This report will mainly focus on multi-angle modeling methods of intelligent robotic systems, solving intelligent robot optimization problems by combining constrained multi-objective evolutionary algorithms and machine learning methods, and applying design automation methods to develop intelligent robots.
摘要：動態多目標優化是目前多目標優化領域的一個研究熱點，目前研究最為廣泛的一種思路是通過預測策略指導算法搜索找到最優解。為了更好的應對不同類型的環境變化，克服單一預測模型在不同類型環境變化下的不穩定性，提出了一種基于集成學習的預測策略（Ensemble Learning-based Prediction Strategy, ELPS）幫助算法重初始化種群以適應新的環境。在ELPS中選取四種不同類型的預測模型作為基模型，包括基于種群的自回歸模型、線性預測模型、基于拐點的自回歸模型及隨機初始化模型。當環境發生改變時，ELPS可以通過對歷史種群進行訓練得到一個強預測模型，并重新生成新種群，實現對環境變化的動態響應。通過ELPS的訓練，可以有效提升預測的準確性并提高種群的多樣性。為了進一步驗證算法在實際問題的性能，選取帶時間窗口的多目標動態車輛路徑規劃問題進行研究，進一步提出了一個基于ELPS的用以求解帶時間窗口的多目標動態車輛路徑規劃問題的算法，選取了隨機初始化策略模型、遷入模型和基于種群的預測模型作為基模型，可以實現對環境不同程度的波動的快速響應，加速種群的收斂速度。
報告七：Role-based Cooperation in Swarm Intelligence
摘要：It is a common phenomenon in human society that allocating different tasks to different people according to their capabilities (or roles). Many studies also verify that assigning different search strategies for different individuals can yield very favorable performance. Furthermore, multi-swarm techniques have been successfully applied in swarm intelligence algorithms (SI) since they can yield very pleasurable performance in keeping population diversity. Inspired by these observations, we integrate multiple roles into SI. In the proposed strategy, the entire population is split into multiple sub-swarms. During the evolutionary process, individuals in each sub-swarm adaptively select their own breeding strategies based on their own roles. Furthermore, the population is regrouped during the evolution process. Thus, different individuals in the same sub-swarm play different roles in a generation. Moreover, an individual may play different roles in different generations, Even a same individual may play different roles in different sub-swarms. Although the role-based cooperation offers a competitive performance testified by the extensive experiments, there are a few problems need to be further studied in future work. The one is the efficiency and effectiveness of the cooperation between different roles need to be in-depth analyzed. The other one is when and how to adjust the population size of different roles to satisfy various fitness landscapes and different evolution stages.