to

### Fusion of Federated Learning and Industrial Internet of Things: A Survey

Industrial Internet of Things (IIoT) lays a new paradigm for the concept of Industry 4.0 and paves an insight for new industrial era. Nowadays smart machines and smart factories use machine learning/deep learning based models for incurring intelligence. However, storing and communicating the data to the cloud and end device leads to issues in preserving privacy. In order to address this issue, federated learning (FL) technology is implemented in IIoT by the researchers nowadays to provide safe, accurate, robust and unbiased models. Integrating FL in IIoT ensures that no local sensitive data is exchanged, as the distribution of learning models over the edge devices has become more common with FL. Therefore, only the encrypted notifications and parameters are communicated to the central server. In this paper, we provide a thorough overview on integrating FL with IIoT in terms of privacy, resource and data management. The survey starts by articulating IIoT characteristics and fundamentals of distributive and FL. The motivation behind integrating IIoT and FL for achieving data privacy preservation and on-device learning are summarized. Then we discuss the potential of using machine learning, deep learning and blockchain techniques for FL in secure IIoT. Further we analyze and summarize the ways to handle the heterogeneous and huge data. Comprehensive background on data and resource management are then presented, followed by applications of IIoT with FL in healthcare and automobile industry. Finally, we shed light on challenges, some possible solutions and potential directions for future research.

### Evaluating Explanation Without Ground Truth in Interpretable Machine Learning

Interpretable Machine Learning (IML) has become increasingly important in many applications, such as autonomous cars and medical diagnosis, where explanations are preferred to help people better understand how machine learning systems work and further enhance their trust towards systems. Particularly in robotics, explanations from IML are significantly helpful in providing reasons for those adverse and inscrutable actions, which could impair the safety and profit of the public. However, due to the diversified scenarios and subjective nature of explanations, we rarely have the ground truth for benchmark evaluation in IML on the quality of generated explanations. Having a sense of explanation quality not only matters for quantifying system boundaries, but also helps to realize the true benefits to human users in real-world applications. To benchmark evaluation in IML, in this paper, we rigorously define the problem of evaluating explanations, and systematically review the existing efforts. Specifically, we summarize three general aspects of explanation (i.e., predictability, fidelity and persuasibility) with formal definitions, and respectively review the representative methodologies for each of them under different tasks. Further, a unified evaluation framework is designed according to the hierarchical needs from developers and end-users, which could be easily adopted for different scenarios in practice. In the end, open problems are discussed, and several limitations of current evaluation techniques are raised for future explorations.

The ability to continuously learn and adapt itself to new tasks, without losing grasp of already acquired knowledge is a hallmark of biological learning systems, which current deep learning systems fall short of. In this work, we present a novel methodology for continual learning called MERLIN: Meta-Consolidation for Continual Learning. We assume that weights of a neural network $\boldsymbol \psi$, for solving task $\boldsymbol t$, come from a meta-distribution $p(\boldsymbol{\psi|t})$. This meta-distribution is learned and consolidated incrementally. We operate in the challenging online continual learning setting, where a data point is seen by the model only once. Our experiments with continual learning benchmarks of MNIST, CIFAR-10, CIFAR-100 and Mini-ImageNet datasets show consistent improvement over five baselines, including a recent state-of-the-art, corroborating the promise of MERLIN.