International Business Machines Corporation

Maplebear Inc.

Supriyo Chakraborty

Dinesh C Verma

Mudhakar Srivatsa

Omer Tripp

Bodhisatwa Sadhu

Raghu Kiran Ganti

Bong Jun Ko

Ramya Raghavendra

Theodoros Salonidis

Christian Makaya

Swati Rallapalli

Xiping Wang

Bongjun Ko

Keith William Grueneberg

Rahul Urgaonkar

Jorge J Ortiz

Shiqiang Wang

Alberto Valdes Garcia

Seraphin Bernard Calo

Nirmit V Desai

Catherine Helen Crawford

Kush Raj Varshney

Saritha Arunkumar

Franck Vinh Le

Akshar Kaul

Hugo M Krawczyk

Joshua M Rosenkranz

Karthikeyan Natesan Ramamurthy

Skyler Speakman

Dennis Wei

Changchang Liu

Mattia Rigotti

Ashish Verma

Jiawei Wen

Amanda Coston

Zairah Mustahsan

A computer-implemented method of determining an agent data attribution and selection to perform a collaborative data-related task includes computing an agent data attribution score for each agent of the plurality of agents associated with the collaborative data-related task. A subset of the plurality of agents that participate in the collaborative data-related task is selected based on the agent data attribution score. An instruction is transmitted to the selected subset of the plurality of agents for each agent to conduct a respective portion of the collaborative data-related task.

Private computation of an agent data attribution score in collaborated task

A method for targeted advertisement includes transmitting a pre-filter to the user device, responsive to contextual information from a user device, to determine, using a processor, one or more inferences based on physical browsing information, collected at the user device, in compliance with one or more privacy policies of the user. The method also includes receiving one or more inferences determined by the pre-filter from the user device and transmitting one or more targeted advertisements to the user device based on one or more inferences.

Recommendations based on private data using a dynamically deployed pre-filter

A method and system of training an interpretable deep learning model includes receiving an input set of data, which may be complex. The input set of data is provided to deep learning model for feature extraction. In an exemplary embodiment, the deep learning model generates a disentangled latent space of features from the feature extraction. The features may comprise semantically meaningful data which is then provided to a low-complexity learning model. The low-complexity learning model generates output based on a specified task (for example, classification or regression). Being a low-complexity learning model provides confidence that the data output from the deep learning model is inherently interpretable.

Using disentangled learning to train an interpretable deep learning model

Techniques for non-iterative federated learning include receiving local models from agents, generating synthetic datasets for the local models, and producing outputs using the local models and the synthetic datasets. A global model is trained based on the synthetic datasets and the outputs.

Non-iterative federated learning

An output time-series of a cell of a neural network is captured. A subset of a set of data points of the output time-series is consolidated into a singular data point. The singular data point is fitted in a data representation to form a quantified aggregated data point. The quantified aggregated data point is included in an intermediate time-series. Using the intermediate time-series as an input at an intermediate layer of the neural network, an anonymized output time-series is produced from the neural network.

Anonymized time-series generation from recurrent neural networks

Embodiments of the invention are directed to a computer-implemented method of distributed learning using a fusion-based approach. The method includes determining data statistics at each system node of a plurality of system nodes, wherein each system node respectively comprises an artificial intelligence model. The method further includes determining a set of control and coordination instructions for training each artificial intelligence model at each system node of the plurality of system nodes. The method further includes directing an exchange of data between the plurality of system nodes based on the data statistics of each system node of the plurality of system nodes. The method further includes fusing trained artificial intelligence models from the plurality of system nodes into a fused artificial intelligence model, wherein the trained artificial intelligence models are trained using the set of control and coordination instructions.

Distributed learning using ensemble-based fusion

A computer implemented method for analyzing network connections includes identifying a connection of interest and a corresponding set of connection data. The method additionally includes generating one or more saliency maps corresponding to the connection of interest. The method additionally includes mapping the generated one or more saliency maps to underlying protocols and fields, and identifying one or more values corresponding to each of the underlying protocols and fields. The method additionally includes extracting general correspondences from the identified one or more values corresponding to each of the underlying protocols and fields.

Network traffic rule identification

Method and apparatus for exchanging corpora via a data broker are provided. One example method generally includes receiving, at the data broker from a holder of a first corpus application, a coreset for the first corpus and transmitting the coreset to a set of data providers. The method further includes receiving, from a first data provider of the set of data providers, a value with respect to the coreset of a second corpus associated with the first data provider and transmitting, from the data broker to the holder of the first corpus, the value. The method further includes receiving, at the data broker from the holder of the first corpus, a request to receive the second corpus and receiving the second corpus from the first data provider. The method further includes validating the value of the second corpus and transmitting the second corpus to the holder of the first corpus.

Determining value of corpora for machine learning using coresets

Neural network protection mechanisms are provided. The neural network protection engine receives a pre-trained neural network computer model and forward propagates a dataset through layers of the pre-trained neural network computer model to compute, for each layer of the pre-trained neural network computer model, inputs and outputs of the layer. For at least one layer of the pre-trained neural network computer model, a differentially private distillation operation is performed on the inputs and outputs of the at least one layer to generate modified operational parameters of the at least one layer. The modified operational parameters of the at least one layer obfuscate aspects of an original training dataset used to train the pre-trained neural network computer model, present in original operational parameters of the at least one layer. The neural network protection engine generates a privatized trained neural network model based on the modified operational parameters.

Layer-wise distillation for protecting pre-trained neural network models

A method of utilizing a computing device to correct source data used in machine learning includes receiving, by the computing device, first data. The computing device corrects the source data via an application of a covariate shift to the source data based upon the first data where the covariate shift re-weighs the source data.

Enhancing fairness in transfer learning for machine learning models with missing protected attributes in source or target domains

Systems and methods for identifying a device are described. In an example, a processor can receive a first signal having a first waveform encoding data. The processor can extract the data from the first signal. The processor can determine a transformation being used to encode the data in the first waveform. The processor can generate a second signal using the determined transformation to encode the data in a second waveform. The processor can determine a difference between the first waveform and the second waveform. The processor can identify a device as a candidate device that sent the first signal, based on the determined difference.

Transmitter identification based on machine learning

Generating an environment information map from a wireless communication system having directional communication capabilities. A plurality of features are extracted and logged resultant from a communication link attempt at multiple beam directions and training at least one machine learning model based on the plurality of extracted features from the first beam direction and the at least one additional beam directions to infer an environment information map of the area between the first transmitter and the receiver.

Method for extracting environment information leveraging directional communication

Techniques for performing root cause analysis in dynamic software testing via probabilistic modeling are provided. In one example, a computer-implemented method includes initializing, by a system operatively coupled to a processor, a threshold value, a defined probability value, and a counter value. The computer-implemented method also includes, in response to determining, by the system, that a probability value assigned to a candidate payload of one or more candidate payloads exceeds the defined probability value, and in response to determining, by the system, that the counter value exceeds the threshold value: determining, by the system, that a match exists between the candidate payload and an input point based on an application of the candidate payload to the input point resulting in a defined condition, wherein the one or more candidate payloads are represented by population data accessed by the system.

Growing community of inventors

White Plains, NY, United States of America

Supriyo Chakraborty