The network pruning algorithm based on evolutionary multi-objective (EMO) can
balance the pruning rate and performance of the network. However, its
population-based nature often suffers from the complex pruning optimization
space and the highly resource-consuming pruning structure verification process,
which limits its application. To this end, this paper proposes an EMO joint
pruning with multiple sub-networks (EMO-PMS) to reduce space complexity and
resource consumption. First, a divide-and-conquer EMO network pruning framework
is proposed, which decomposes the complex EMO pruning task on the whole network
into easier sub-tasks on multiple sub-networks. On the one hand, this
decomposition reduces the pruning optimization space and decreases the
optimization difficulty; on the other hand, the smaller network structure
converges faster, so the computational resource consumption of the proposed
algorithm is lower. Secondly, a sub-network training method based on
cross-network constraints is designed so that the sub-network can process the
features generated by the previous one through feature constraints. This method
allows sub-networks optimized independently to collaborate better and improves
the overall performance of the pruned network. Finally, a multiple sub-networks
joint pruning method based on EMO is proposed. For one thing, it can accurately
measure the feature processing capability of the sub-networks with the
pre-trained feature selector. For another, it can combine multi-objective
pruning results on multiple sub-networks through global performance impairment
ranking to design a joint pruning scheme. The proposed algorithm is validated
on three datasets with different challenging. Compared with fifteen advanced
pruning algorithms, the experiment results exhibit the effectiveness and
efficiency of the proposed algorithm.

本研究提出一种基于进化多目标（EMO）算法的网络修剪算法，结合多子网络来降低空间复杂度和资源消耗，其中提出了分而治之的 EMO 网络修剪框架和基于交叉网络约束的子网络训练方法，并设计了多子网络联合修剪方法来优化整个修剪网络的性能。实验结果表明，此算法比十五种先进的修剪算法更为有效和高效。

EMO 联合剪枝与多个子网络：快速高效

An EMO Joint Pruning with Multiple Sub-networks: Fast and Effect

In this paper, an online task scheduling and mapping method based on a fuzzy
neural network (FNN) learned by an evolutionary multi-objective algorithm
(NSGA-II) to jointly optimize the main design challenges of heterogeneous
MPSoCs is proposed. In this approach, first, the FNN parameters are trained
using an NSGA-II-based optimization engine by considering the main design
challenges of MPSoCs including temperature, power consumption, failure rate,
and execution time on a training dataset consisting of different application
graphs of various sizes. Next, the trained FNN is employed as an online task
scheduler to jointly optimize the main design challenges in heterogeneous
MPSoCs. Due to the uncertainty in sensor measurements and the difference
between computational models and reality, applying the fuzzy neural network is
advantageous in online scheduling procedures. The performance of the method is
compared with some previous heuristic, meta-heuristic, and rule-based
approaches in several experiments. Based on these experiments our proposed
method outperforms the related studies in optimizing all design criteria. Its
improvement over related heuristic and meta-heuristic approaches are estimated
10.58% in temperature, 9.22% in power consumption, 39.14% in failure rate, and
12.06% in execution time, averagely. Moreover, considering the interpretable
nature of the FNN, the frequently fired extracted fuzzy rules of the proposed
approach are demonstrated.

提出了一种基于模糊神经网络（FNN）及 NSGA-II 进化多目标算法的在线任务调度和映射方法，以共同优化异构 MPSoC 的主要设计挑战。通过实验验证，该方法优于相关启发式和元启发式方法，可以提高温度，功耗，故障率和执行时间等几个设计指标的优化性能。