International Business Machines Corporation

Bong Jun Ko

Dinesh C Verma

Kang-Won Lee

Ramya Raghavendra

Vasileios Pappas

Theodoros Salonidis

Seraphin Bernard Calo

Raheleh B Dilmaghani

Yang Song

Rahul Urgaonkar

Mudhakar Srivatsa

Swati Rallapalli

Shiqiang Wang

Murtaza Zafer

Nirmit V Desai

Jorge J Ortiz

Dakshi Agrawal

Supriyo Chakraborty

Christian Makaya

Xiping Wang

Vinay Kumar Kolar

Wei-Han Lee

Robert Bruce Nicholson

Bodhisatwa Sadhu

Raghu Kiran Ganti

Thai Franck Le

Keith William Grueneberg

Changchang Liu

Tiffany Tuor

Douglas Morgan Freimuth

Shivkumar Kalyanaraman

Erich Miles Nahum

Chatschik Bisdikian

Ravi Kothari

Petros Zerfos

Joel W Branch

Maroun Touma

Shahrokh Daijavad

Parul Gupta

Joshua M Rosenkranz

Ho Yin Starsky Wong

Alina Beygelzimer

Irene Lizeth Manotas Gutierrez

Shonda A Witherspoon

Shalisha Witherspoon

Yuang Jiang

Methods and systems for execution of distributed analytics include building a global linked structure that describes correspondences between dataset metadata structures, analytics metadata structures, and location metadata structures and that encodes compatibility between respective datasets, analytics, and locations. A set of analytics and compatible datasets for execution is determined based on the dataset metadata structures, analytics metadata structures, and global linked structure. An optimal execution location is determined based on the determined set of analytics and compatible datasets, the location metadata structures, and the global linked structure. The set of analytics and compatible datasets are deployed to the optimal location for execution.

Linking, deploying, and executing distributed analytics with distributed datasets

A data mining method, system, and non-transitory computer readable medium include obtaining a subset of public records of data in a public domain and performing data mining, via private domain data, within the subset of the public records of data to find data in the public domain corresponding to a particular individual.

System, method, and recording medium for data mining between private and public domains

Methods are provided. A method includes announcing to a network meta information describing each of a plurality of distributed data sources. The method further includes propagating the meta information amongst routing elements in the network. The method also includes inserting into the network a description of distributed datasets that match a set of requirements of the analytics task. The method additionally includes delivering, by the routing elements, a copy of the analytics task to locations of respective ones of the plurality of distributed data sources that include the distributed datasets that match the set of requirements of the analytics task.

Content-based distribution and execution of analytics applications on distributed datasets

A provenance method, system, and non-transitory computer readable medium for a plurality of eidetic systems having logs, include crawling the logs of each node of a plurality of nodes of the eidetic systems to cluster segments across the logs of temporally correlated events into clustered segments and analyzing the correlated segments to interleave an order of processes in the logs and assign a probability to the order of the processes occurring.

System, method, and recording medium for distributed probabilistic eidetic querying, rollback, and replay

Embodiments are disclosed for a method for a wearable secure data device. The method includes setting an operational mode for the wearable secure data device that stores a plurality of secure data items. The method also includes receiving a request for at least one of the secure data items from a client device that is communicating with a third-party device. Additionally, the method includes determining if the operational mode is associated with allowing access to the secure data items. Further, the method includes providing a response based on the determination.

Wearable secure data device

A computer-implemented method, a computer program product, and a computer system for incremental and decentralized pruning of a machine learning model in federated learning. A federated learning system determines a serial sequence of participating in model pruning by agents in the federated learning system. A server in the federated learning system sends, to a first agent in the serial sequence, an initial model to trigger a federated pruning process for the machine learning model. The each of agents in the serial sequence prunes the machine learning model. The each of agents in the serial sequence generates an intermediately pruned model for an immediately next agent to prune. A final agent in the serial sequence prunes the machine learning model and generates a finally pruned model. The final agent sends the finally pruned model to the server.

Incremental and decentralized model pruning in federated machine learning

A training process of a machine learning model is executed at the edge node for a number of iterations to generate a model parameter based at least in part on a local dataset and a global model parameter. A resource parameter set indicative of resources available at the edge node is estimated. The model parameter and the resource parameter set are sent to a synchronization node. Updates to the global model parameter and the number of iterations are received from the synchronization node based at least in part on the model parameter and the resource parameter set of edge nodes. The training process of the machine learning model is repeated at the edge node to determine an update to the model parameter based at least in part on the local dataset and updates to the global model parameter and the number of iterations from the synchronization node.

Distributed machine learning at edge nodes

A data mining method, system, and non-transitory computer readable medium, include defining a set of filter constraints as a filter function for clustering users' private records of data of a private domain, selecting a subset of users' public records of data from a filtered set of data from a public domain that is common with the users' private records of data, and creating a data file including the matched user of the private domain to the public records of the user of the private domain, where the set of the filter constraints comprises a function that captures the subset of the users' public records of data who are of interest to the private domain, and only performs data mining with that set of information from the public domain.

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

A method, a computer program product, and a computer system determine when to perform a federated learning process. The method includes identifying currently available contributors among contributors of a federated learning task for which the federated learning process is to be performed. The method includes determining a usefulness metric of the currently available contributors for respective datasets from each of the currently available contributors used in performing the federated learning process. The method includes, as a result of the usefulness metric of the currently available contributors being at least a usefulness threshold, generating a recommendation to perform the federated learning process with the datasets of the currently available contributors. The method includes transmitting the recommendation to a processing component configured to perform the federated learning process.

Federated learning of clients

Aspects of the invention include methods of performing beam management in a base station of a cellular network. A method includes obtaining, at the base station, information indicating whether one or more terminals of the cellular network have data to transmit, and determining, using the base station, during a sweep by the base station if an upcoming terminal has data to transmit based on the information. The sweep by the base station is a sequential movement of the beam over a coverage area. The method also includes foregoing, by the base station, any communication with the upcoming terminal during the sweep based on the information indicating that the upcoming terminal has no data to transmit, and communicating, using the base station, with the upcoming terminal during the sweep based on the information indicating that the upcoming terminal has data to transmit.

Base station beam management based on terminal transmit data indication

A computer-implemented method for delivering network connectivity includes receiving, by an edge server, a set of communication packets from a communication device. The method further includes storing, by the edge server, the set of communication packets as part of outbound data. The method further includes determining, by the edge server, that a mobile access point is within a communicable range of the edge server. The mobile access point travels back and forth between the edge server and a base station. The method further includes transmitting, by the edge server, the outbound data to the mobile access point that is within the communicable range.

Cost effective delivery of network connectivity to remote areas

Audio data of an original work is received. Text in the audio data is translated to a target language. The audio data is passed to a first deep learning model to learn voice features in the audio data. The audio data is passed to a second deep learning model to learn audio properties in the audio data. The translated text is synchronized to play in the position of original text of the original work in a synthesized voice. A translated audio data of the original work is created by combining the synchronized translated text in the synthesized voice with music of the audio data.

Automatic translation using deep learning

A GAN includes a first device and a second device. A discriminator model in the first device is trained to discriminate samples from a transmitter in the first device from samples from other transmitters, by collaborating by the first device with the second device to train the discriminator model to discriminate between samples from its transmitter and spoofed samples received from a generator model in the second device and to train the generator model in the second device to produce more accurate spoofed samples received by the first device during the training. The training results in a trained discriminator model, which is distributed to another device for use by the other device to discriminate samples received by the other device in order to perform authentication of the transmitter in the first device. The other device performs authentication of the transmitter of the first device using the distributed model.

Efficient bootstrapping of transmitter authentication and use thereof

Growing community of inventors

Harrington Park, NJ, United States of America

Bong Jun Ko