This paper is the second part of a two-part series on evolutionary sequential transfer optimization (ESTO). The first part designs a problem generator to generate benchmark problems with diverse properties that can better resemble real-world problems. This part proposes five research questions (RQs) to empirically revisit a large body of knowledge transfer techniques in the context of solution-based ESTO (S-ESTO). Particularly, knowledge transfer techniques are organized from a perspective of transfer strategy, including solution selection, solution adaptation, and the integration of them. The results reveal that the performance of many algorithms is highly sensitive to similarity distribution of STOPs, which suggest the necessity of more flexible algorithm design in future studies. Specifically, when an STOP is full of source tasks that are highly similar to the target task in terms of optimum, one can randomly select one source task and reuse its elite solution(s) to accelerate the target search significantly. When an STOP contains source tasks with mixed similarities to the target task, an effective similarity metric that can represent the transferability is able to identify highly transferable solution(s). When an STOP is full of source tasks with low similarities to the target task, the transferability is expected to be improved by solution adaptation. In solution adaptation, a similarity metric in the form of a maximization (or minimization) objective function that is responsible for representing the transferability is optimized to obtain a mapping function for adapting source solution(s). The source code for reproducing our experiments is available at https://github.com/XmingHsueh/Revisiting-S-ESTOs-PartB.
