System and method for processing a graph that defines a set of nodes and a set of edges, the nodes each having an associated set of node attributes, the edges each representing a relationship that connects two respective nodes, comprising: generating a first node embedding for each node by: generating, for the node and each of a plurality of neighbour nodes, a respective first edge attribute defining a respective relationship type between the node and the neighbour node based on the node attributes of the node and the node attributes of the neighbour node; generating a first neighborhood vector that aggregates information from the generated first edge attributes and the node attributes of the neighbour nodes; generating the first node embedding based on the node attributes of the node and the generated first neighborhood vector.

Techniques described herein relate to a method for model updating in a federated learning environment. The method may include distributing, by a model coordinator, a current model to a plurality of client nodes; receiving, by the model coordinator and in response to distributing the current model, a set of gradient K-quant vectors, wherein each gradient K-quant vector of the first set of gradient K-quant vectors is received from one client node of the plurality of client nodes. The gradient K-quant vectors may be compressed representations of gradient vectors. The compression may be performed by determining a bin index value corresponding to the gradient vector values, based on a K value and range received from the model coordinator. The model coordinator may use the gradient K-quant vectors to generate an updated model, and send the updated model to the client nodes for use in the next training cycle.

Embodiments of the present disclosure relate to a model optimization method, an electronic device, and a computer program product. This method includes: determining an initial learning rate combination for a deep learning model, wherein the initial learning rate combination includes a plurality of learning rates, each learning rate being determined for one of a plurality of layers of the deep learning model, and the plurality of learning rates including static learning rates and dynamic learning rates; and adjusting the initial learning rate combination to obtain a target learning rate combination, wherein an accuracy rate achieved when the target learning rate combination is used to train the deep learning model is higher than or equal to a first threshold accuracy rate. With the technical solution of the present disclosure, a deep learning model can be optimized by setting learning rates for each layer of the deep learning model.

Techniques for detecting impactful performance anomalies in storage systems. The techniques include obtaining, for each performance metric of a storage system's workload, a training set of series diffs based on a threshold. Each diff represents a difference between an observed value from an observed set of time series values for the performance metric and a normalized value from a corresponding set of normalized time series values. The techniques include applying the training set of series diffs for each performance metric to an unsupervised anomaly detection algorithm and running the algorithm to identify potentially impactful anomalies in a multi-dimensional search space. The techniques include identifying impactful anomalies from among the potentially impactful anomalies that exceed an anomaly score. In this way, impactful anomalies having a causal effect on multiple performance metrics of the storage system's workload can be identified in a manner less complex and less costly than prior multivariate approaches.

Techniques for detecting impactful performance anomalies in storage systems. The techniques include obtaining, for each performance metric of a storage system's workload, a training set of series diffs based on a threshold. Each diff represents a difference between an observed value from an observed set of time series values for the performance metric and a normalized value from a corresponding set of normalized time series values. The techniques include applying the training set of series diffs for each performance metric to an unsupervised anomaly detection algorithm and running the algorithm to identify potentially impactful anomalies in a multi-dimensional search space. The techniques include identifying impactful anomalies from among the potentially impactful anomalies that exceed an anomaly score. In this way, impactful anomalies having a causal effect on multiple performance metrics of the storage system's workload can be identified in a manner less complex and less costly than prior multivariate approaches.

Computer-implemented methods, program products, and systems for provenance-based defense against poison attacks are disclosed. In one approach, a method includes: receiving observations and corresponding provenance data from data sources; determining whether the observations are poisoned based on the corresponding provenance data; and removing the poisoned observation(s) from a final training dataset used to train a final prediction model. Another implementation involves provenance-based defense against poison attacks in a fully untrusted data environment. Untrusted data points are grouped according to provenance signature, and the groups are used to train learning algorithms and generate complete and filtered prediction models. The results of applying the prediction models to an evaluation dataset are compared, and poisoned data points identified where the performance of the filtered prediction model exceeds the performance of the complete prediction model. Poisoned data points are removed from the set to generate a final prediction model.

An example operation includes one or more of sensing from at least one sensor, a longitudinal acceleration and a lateral acceleration, receiving from the at least one sensor, a longitudinal acceleration signal based on the longitudinal acceleration and a lateral acceleration signal based on the lateral acceleration, filtering via at least one logic, the longitudinal acceleration signal and the lateral acceleration signal based on an interquartile range of the longitudinal acceleration signal and the lateral acceleration signal, yielding a plurality of filtered signals and determining via the at least one logic, a mobility index of a transport based on the filtered signals.

An example operation includes one or more of sensing from at least one sensor, a longitudinal acceleration and a lateral acceleration, receiving from the at least one sensor, a longitudinal acceleration signal based on the longitudinal acceleration and a lateral acceleration signal based on the lateral acceleration, filtering via at least one logic, the longitudinal acceleration signal and the lateral acceleration signal based on an interquartile range of the longitudinal acceleration signal and the lateral acceleration signal, yielding a plurality of filtered signals and determining via the at least one logic, a mobility index of a transport based on the filtered signals.

One embodiment includes a computer-implemented data labeling platform. The platform provides a confidence-driven workflow (CDW) executable to receive and process labeling requests to label data items. The CDW comprises a set of executable labelers, each labeler in having a dynamically modeled confidence range. The execution path for processing a labeling request to label a data item is dynamically determined. Dynamically determining the execution path comprises dynamically determining a bounded number of candidate paths through the set of labelers using dynamically calculated cost and confidence metrics for the labelers in the set of labelers to estimate a probability of each candidate path to satisfy a set of constraints on cost and final result confidence, selecting a candidate path that minimizes cost for a specified confidence from the candidate paths as a selected path, executing a next labeler consultation according to the selected path to label the data item, and dynamically re-determining the remaining execution path using calculated results arising from executing the completed path steps.

Embodiments include a system for determining cardiovascular information for a patient. The system may include at least one computer system configured to receive patient-specific data regarding a geometry of the patient's heart, and create a three-dimensional model representing at least a portion of the patient's heart based on the patient-specific data. The at least one computer system may be further configured to create a physics-based model relating to a blood flow characteristic of the patient's heart and determine a fractional flow reserve within the patient's heart based on the three-dimensional model and the physics-based model.