To overcome this challenge, diverging from conventional efforts of expanding the solver's search scope, we focus on enabling information to actively propagate to the solver through heat diffusion.

Utilizing mutual learning can effectively enhance the performance of peer BNNs.

Furthermore, the exploration of temporal context information within PSs is also a serious challenge.

Critical in this context is the prior knowledge accumulated from related tasks.

Fréchet regression has emerged as a promising approach for regression analysis involving non-Euclidean response variables.