Abstract: Techniques for performing predictability-driven compression of training data sets used for machine learning (ML) are provided. In one set of embodiments, a computer system can receive a training data set comprising a plurality of data instances and can train an ML model using the plurality of data instances, the training resulting in a trained version of the ML model. The computer system can further generate prediction metadata for each data instance in the plurality of data instances using the trained version of the ML model and can compute a predictability measure for each data instance based on the prediction metadata, the predictability measure indicating a training value of the data instance. The computer system can then filter one or more data instances from the plurality of data instances based on the computed predictability measures, the filtering resulting in a compressed version of the training data set.

Abstract: In one set of embodiments, a deep reinforcement learning (RL) system can train an agent to construct an efficient decision tree for classifying network packets according to a rule set, where the training includes: identifying, by an environment of the deep RL system, a leaf node in a decision tree; computing, by the environment, a graph structure representing a state of the leaf node, the graph structure including information regarding how one or more rules in the rule set that are contained in the leaf node are distributed in a hypercube of the leaf node; communicating, by the environment, the graph structure to the agent; providing, by the agent, the graph structure as input to a graph neural network; and generating, by the graph neural network based on the graph structure, an action to be taken on the leaf node for extending the decision tree.

Abstract: In one set of embodiments, a client can receive from a server a copy of a neural network from a server including N layers. The client can further provide one or more data instances as input to the copy, the one or more data instances being part of a local training data set residing on the client, compute a client gradient comprising gradient values for the N layers, determine a partial client gradient comprising gradient values for a first K out of the N layers, and determine an output of a K-th layer of the copy, the output being a result of processing performed by the first K layers on the one or more data instances. The client can then transmit the partial client gradient and the output of the K-th layer to the server.

Abstract: In one set of embodiments, a computer system can receive an unlabeled dataset comprising a plurality of unlabeled data instances, each unlabeled data instance including values for a plurality of features. The computer system can train, for each feature, a supervised machine learning (ML) model on a labeled dataset derived from the unlabeled dataset, where the labeled dataset comprises a plurality of labeled data instances, and wherein each labeled data instance includes (1) a label corresponding to a value for the feature in an unlabeled data instance of the unlabeled dataset, and (2) values for other features in the unlabeled data instance. The computer system can then compute, for each pair of first and second features in the plurality of features, an inter-feature influence score using the trained supervised ML model for the second feature, the inter-feature influence score indicating how useful the first feature is in predicting the second feature.

Abstract: In one set of embodiments, a computer system can receive a query data instance for which a prediction is requested and transmit the query data instance to a plurality of computing nodes. The computer system can further receive, from each computing node, a per-node prediction for the query data instance, where the per-node prediction is generated by the computing node using a trained version of a local machine learning (ML) model of the computing node and where the per-node prediction is encrypted in a manner that prevents the query server from learning the per-node prediction. The computer system can then aggregate the per-node predictions, generate a federated prediction based on the aggregated per-node predictions, and output the federated prediction as a final prediction result for the query data instance.

Abstract: In one set of embodiments, a computing node in a plurality of computing nodes can train a first ML model on a local training dataset comprising a plurality of labeled training data instances, where the training is performed using a distributed/federated training approach across the plurality of computing nodes and where the training results in a trained version of the first ML model. The computing node can further compute, using the trained version of the first ML model, a training value measure for each labeled training data instance in the local training dataset and identify a subset of the plurality of labeled training data instances based on the computed training value measures. The computing node can then train a second ML model on the subset, where the training of the second ML model is performed using the distributed/federated training approach.

Abstract: Techniques for implementing unsupervised anomaly detection via supervised methods are provided. In one set of embodiments, a computer system can train an unsupervised anomaly detection classifier using an unlabeled training data set and classify the unlabeled training data set via the trained version of the unsupervised classifier, where the classifying generates anomaly scores for the data instances in the unlabeled training data set. The computer system can further construct a labeled training data set that includes a first subset of data instances from the unlabeled training data set whose anomaly scores are below a first threshold and a second subset of data instances from the unlabeled training data set whose anomaly scores are above a second threshold. The computer system can then train a supervised anomaly detection classifier using the labeled training data set.

Abstract: Techniques for quantizing training data sets using machine learning (ML) model metadata are provided. In one set of embodiments, a computer system can receive a training data set comprising a plurality of features and a plurality of data instances, where each data instance includes a feature value for each of the plurality of features. The computer system can further train a machine learning (ML) model using the training data set, where the training results in a trained version of the ML model, and can extract metadata from the trained version of the ML model pertaining to the plurality of features. The computer system can then quantize the plurality of data instances based on the extracted metadata, the quantizing resulting in a quantized version of the training data set.

Abstract: Techniques for augmenting training data sets for machine learning (ML) classifiers using classification metadata are provided. In one set of embodiments, a computer system can train a first ML classifier using a training data set, where the training data set comprises a plurality of data instances, where each data instance includes a set of features, and where the training results in a trained version of the first ML classifier. The computer system can further classify each data instance in the plurality of data instances using the trained version of the first ML classifier, the classifications generating classification metadata for each data instance, and augment the training data set with the classification metadata to create an augmented version of the training data set. The computer system can then train a second ML classifier using the augmented version of the training data set.

Abstract: Techniques for training a neural network classifier using classification metadata from another, non-neural network (non-NN) classifier are provided. In one set of embodiments, a computer system can train the non-NN classifier using a training data set, where the training results in a trained version of the non-NN network classifier. The computer system can further classify a data instance in the plurality of data instances using the trained non-NN classifier, the classifying generating a first class distribution for the data instance, and provide the data instance's feature set as input to a neural network classifier, the providing causing the neural network classifier to generate a second class distribution for the data instance.

Abstract: Techniques for implementing a tree-based ensemble classifier comprising an internal load balancer are provided. In one set of embodiments, the tree-based ensemble classifier can receive a query data instance and select, via the internal load balancer, a subset of its decision trees for processing the query data instance. The tree-based ensemble classifier can then query each decision tree in the selected subset with the query data instance, combine the per-tree classifications generated by the subset trees to generate a subset classification, and determine whether a confidence level associated with the subset classification is sufficiently high. If the answer is yes, the tree-based ensemble classifier can output the subset classification as a final classification result for the query data instance. If the answer is no, the tree-based ensemble classifier can repeat the foregoing steps until a sufficient confidence level is reached or until all of its decision trees have been selected and queried.

Abstract: Techniques for implementing unsupervised anomaly detection by self-prediction are provided. In one set of embodiments, a computer system can receive an unlabeled training data set comprising a plurality of unlabeled data instances, where each unlabeled data instance includes values for a plurality of features. The computer system can further train, for each feature in the plurality of features, a supervised machine learning (ML) model using a labeled training data set derived from the unlabeled training data set, receive a query data instance, and generate a self-prediction vector using at least a portion of the trained supervised ML models and the query data instance, where the self-prediction vector indicates what the query data instance should look like if it were normal. The computer system can then generate an anomaly score for the query data instance based on the self-prediction vector and the query data instance.

Abstract: Techniques for performing predictability-driven compression of training data sets used for machine learning (ML) are provided. In one set of embodiments, a computer system can receive a training data set comprising a plurality of data instances and can train an ML model using the plurality of data instances, the training resulting in a trained version of the ML model. The computer system can further generate prediction metadata for each data instance in the plurality of data instances using the trained version of the ML model and can compute a predictability measure for each data instance based on the prediction metadata, the predictability measure indicating a training value of the data instance. The computer system can then filter one or more data instances from the plurality of data instances based on the computed predictability measures, the filtering resulting in a compressed version of the training data set.

Abstract: Techniques for implementing intelligent data partitioning for a distributed machine learning (ML) system are provided. In one set of embodiments, a computer system implementing a data partition module can receive a training data instance for a ML task and identify, using a clustering algorithm, a cluster to which the training data instance belongs, the cluster being one of a plurality of clusters determined via the clustering algorithm that partition a data space of the ML task. The computer system can then transmit the training data instance to a ML worker of the distributed ML system that is assigned to the cluster, where the ML worker is configured to build or update a ML model using the training data instance.

Abstract: A method and system for configuring an optical circuit switch is provided. Configuring includes sampling for demand estimation at buffers of an electrical packet switch that is either directly connected to the optical circuit switch, or is dynamically routed to a physical port that is connected to the optical circuit switch. Configuring is performed based on the demand estimation at a port on the electrical packet switch exceeding a first dynamic threshold. The optical circuit can be released based on the demand estimation at the port on the electrical packet switch receding a second dynamic threshold, and the second dynamic threshold is less than the first dynamic threshold.