Abstract: Techniques are disclosed for explainable federated learning. An example method includes receiving, at a central node, relative importances for a plurality of features input into a machine learning (ML) model usable at an edge node, thereby defining a plurality of feature importances, the central node being configured to communicate with the edge nodes; using, at the central node, an ML algorithm to classify the edge nodes into a number ‘k’ of node groups based on the feature importances; and for each node group among the ‘k’ node groups: generating, at the central node, an ML shared model using the feature importances associated with a selected subset of nodes in the node group; and deploying, at the central node, the shared model to each edge node in the node group.

Abstract: Techniques are disclosed for sparse layer-wise training of neural networks. An example system includes at least one processing device including a processor coupled to a memory. The at least one processing device can be configured to implement the following steps: obtaining class predictions while saving activations for only a number ‘k’ layers of a neural network, using the class predictions to calculate a layer shallowness measure for the neural network, using the layer shallowness measure to determine a number ‘u’ of layers to update in the neural network, and partially updating the neural network by training only the number ‘u’ layers of the neural network.

Abstract: One example method includes, at a client that is part of a group of clients, where each client in the group is able to communicate with the other clients of the group, performing operations that include training a machine learning (ML) model hosted at the client, based on predictions generated by the ML model in response to input data received by the ML model, labeling selected data of the input data, retraining the ML model, to create an updated ML model, using the selected data, computing a set of metrics based on performance of the updated ML model, compiling the set of metrics into a reliable model exchange and aggregation score (RMEAS), and based on the RMEAS, determining whether to engage in an exchange, with one or more of the other clients, involving the updated ML model.

Abstract: A framework for extracting quantitative and comparable explanations in terms of feature-value ranges for anomaly detection models based on outlier scores is disclosed. In a first phase, outlier scores are computed for a data set. In a second phase, thresholds per feature, which are used to identify abnormal entries or records in the data set, are extracted. In a third phase, a map between feature-outlier scores and feature-value ranges is generated. The feature-value ranges represent explanations. The explanations may include extracting quantitative metrics to explain a model.

Abstract: One example method includes evaluating a set of itemsets, based on the evaluating, computing association rules corresponding to the itemsets, filtering the association rules to identify relevant association rules, sorting the relevant association rules according to their respective metrics of support, confidence, lift, and conviction, and the relevant association rules are sorted from best metrics to worst metrics, storing (1) best itemsets of the set of itemsets, and (2) the association rules with the best metrics, as thresholds, mapping the thresholds to the stored association rules and to feature-value ranges, and identifying the stored association rules and the feature-value ranges as root causes of an anomaly, and explanations of the anomaly, respectively.

Abstract: One example method includes receiving, by a server from each client in a group of clients, metrics and parameters of local models relating to training of a model by the client, aggregating, by the server, the model parameters, determining, by the server using the metrics that have been sent, if a convergence criterion for the model has been met, and when the convergence criterion is determined not to have been met, calculating, by the server, a respective ? value for each of the clients, and transmitting, by the server to the clients, the respective ? values, and the ? values respectively indicate, to the clients, an extent to which the client should perform exploration, and/or exploitation, in a next training round for the model.