Microsoft Technology Licensing, LLC

Rovi Technologies Corporation

Other

Intel Corporation

Nir Nice

Noam Koenigstein

Oren Barkan

John Eugene Neystadt

Itzik Malkiel

Ulrich Paquet

Michael Feldman

Daniel Sitton

Oleg Ananiev

John F Wohlfert

Roy Hirsch

Dror Kremer

Nimrod Ben Simhon

Meir Mendelovich

Ori Katz

Noam Gershon Ben-Yochanan

Ken Aoyama

Shahar Keren

Shay Yehuda Gurman

Ayelet Kroskin

Avi Caciularu

Efim Hudis

Anat Eyal

Yigal Mordechai Edery

Amit Finkelstein

Tomer Shiran

Noam Razin

Dvir Ginzburg

Yonathan Weill

Ying Li

Eyal Krupka

Melissa Wood Dunn

Yacov Yacobi

Ran Gilad-Bachrach

Uri Barash

Arie Friedman

Ehud Wieder

Eugene John Neystadt

Liran Katzir

Boaz Feldbaum

Alexander Teplitsky

Samer J Karim

Sefy Ophir

Shimon Shlevich

William Henry Gates, Iii

Alexander G Gounares

Paul J Leach

Philip Derbeko

Todd R Manion

Benjamin M Schultz

Boyd Cannon Multerer

Michael Joseph Toutonghi

Ashwin Palekar

Cynthia Dwork

Hen Fitoussi

David Richard Reed

Shai Herzog

Narasimhan Agrahara Venkataramaiah

Ron Mondri

Rushmi U Malaviarachchi

Jeromy Scott Statia

Michael Goldbach

Gennady Medvinsky

Teresa Mah

Boaz Ein-Gil

Lee Walker

Max Uritsky

Matthew Jason Pope

Joshua C Zana

Omri Armstrong

Amos Ortal

Darrell J Cannon

Gal Lavee

Sara Bitan

Sreenivas Addagatla

Chandrasekhar Nukala

Shyam Sujeewa Habarakada

Anat Bar-Anan

Amir Hertz

Paul Nogues

Yehuda Finkelstein

Shai Roitman

Alik Teplitsky

Shyam Seshadri

Eran Shamir

Vu Anh Ha

Eric Picard

Ahmad Masri

Lior Alon

Shay Ben-Elazar

David B Cross

Craig Alan Nelson

Paresh Ramchandra Haridas

Eylon Yogev

Shay Ben Elazar

Yehiel Berezin

Tal Zaccai

Amit Shaked

Eric Don Van Valkenburg

Friedman Arie

A method of training a machine learning model is provided. The method includes receiving labeled training data in the machine learning model, the received labeled training data including content data for items accessible to a user and input usage data representing recorded interaction between the user and the items, wherein the received content data for each item includes data representing intrinsic attributes of the item. The method further includes selecting a set of the input usage data that excludes input usage data for a proper subset of the items and training the machine learning model based on both the content data and the selected set of input usage data of the received labeled training data for the items.

Model with usage data compensation

A relational similarity determination engine receives as input a dataset including a set of entities and co-occurrence data that defines co-occurrence relations for pairs of the entities. The relational similarity determination engine also receives as input side information defining explicit relations between the entities. The relational similarity determination engine jointly models the co-occurrence relations and the explicit relations for the entities to compute a similarity metric for each different pair of entities within the dataset. Based on the computed similarity metrics, the relational similarity determination engine identifies a most similar replacement entity from the dataset for each of the entities within the dataset. For a select entity received as an input, the relational similarity determination engine outputs the identified most similar replacement entity.

Representation learning with side information

A method of generating an aggregate saliency map using a convolutional neural network. Convolutional activation maps of the convolutional neural network model are received into a saliency map generator, the convolutional activation maps being generated by the neural network model while computing the one or more prediction scores based on unlabeled input data. Each convolutional activation map corresponds to one of the multiple encoding layers. The saliency map generator generates a layer-dependent saliency map for each encoding layer of the unlabeled input data, each layer-dependent saliency map being based on a summation of element-wise products of the convolutional activation maps and their corresponding gradients. The layer-dependent saliency maps are combined into the aggregate saliency map indicating the relative contributions of individual components of the unlabeled input data to the one or more prediction scores computed by the convolutional neural network model on the unlabeled input data.

Deep gradient activation map model refinement

Aspects of the technology described herein use acoustic features of a music track to capture information for a recommendation system. The recommendation can work without analyzing label data (e.g., genre, artist) or usage data for a track. For each audio track, a descriptor is generated that can be used to compare the track to other tracks. The comparisons between track descriptors result in a similarity measure that can be used to make a recommendation. In this process, the audio descriptors are used directly to form a track-to-track similarity measure between tracks. By measuring the similarity between a track that a user is known to like and an unknown track, a decision can be made whether to recommend the unknown track to the user.

Song similarity determination

An anchor-based collaborative filtering system receives a training dataset including user-item interactions each identifying a user and an item that the user has positively interacted with. The system defines a vector space and distributes the items of the training dataset within the vector based on a determined similarity of the items. The system further defines a set of taste anchors that are each associated in memory with a subgroup of the items in a same neighborhood of the vector space. To make a recommendation to an individual user, the system identifies an anchor-based representation for the individual user that includes a subset of the defined taste anchors that best represents the types of items that the user has favorably interacted with in the past. The taste anchors included in the identified anchor-based representation for the individual user are used to make recommendations to the user in the future.

Anchor-based collaborative filtering

Machine learning multiple features of an item depicted in images. Upon accessing multiple images that depict the item, a neural network is used to machine train on the plurality of images to generate embedding vectors for each of multiple features of the item. For each of multiple features of the item depicted in the images, in each iteration of the machine learning, the embedding vector is converted into a probability vector that represents probabilities that the feature has respective values. That probability vector is then compared with a value vector representing the actual value of that feature in the depicted item, and an error between the two vectors is determined. That error is used to adjust parameters of the neural network used to generate the embedding vector, allowing for the next iteration in the generation of the embedding vectors. These iterative changes continue thereby training the neural network.

Machine learning multiple features of depicted item

The disclosed distributed task coordination ensures task execution while minimizing both the risk of duplicate execution and resources consumed for coordination. Execution is guaranteed, while only best efforts are used to avoid duplication. Example solutions include requesting, by a node, a first lease from a first set of nodes; based at least on obtaining at least one first lease, requesting, by the node, a second lease from a second set of nodes; based at least on the node obtaining at least one second lease, determining a majority holder of second leases; and based at least on obtaining the majority of second leases, executing, by the node, a task associated with the at least one second lease. In some examples, the nodes comprise online processing units (NPUs). In some examples, if a first node begins executing the task and fails, another node automatically takes over to ensure completion.

Multi-phase distributed task coordination

Examples provide a self-supervised language model for document-to-document similarity scoring and ranking long documents of arbitrary length in an absence of similarity labels. In a first stage of a two-staged hierarchical scoring, a sentence similarity matrix is created for each paragraph in the candidate document. A sentence similarity score is calculated based on the sentence similarity matrix. In the second stage, a paragraph similarity matrix is constructed based on aggregated sentence similarity scores associated with the first candidate document. A total similarity score for the document is calculated based on the normalize the paragraph similarity matrix for each candidate document in a collection of documents. The model is trained using a masked language model and intra-and-inter document sampling. The documents are ranked based on the similarity scores for the documents.

Self-supervised document-to-document similarity system

The disclosure herein describes a system for interpreting text-based similarity between a seed item and a recommended item selected by a pre-trained language model from a plurality of candidate items based on semantic similarities between the seed item and the recommended item. The system analyzes similarity scores and contextual paragraph representations representing text-based descriptions of the seed item and recommended item to generate gradient maps and word scores representing the text-based descriptions. A model for interpreting text-based similarity utilizes the calculated gradients and word scores to match words from the seed item description with words in the recommended item description having similar semantic meaning. The word-pairs having the highest weight are identified by the system as the word-pairs having the greatest influence over the selection of the recommended item from the candidate items by the original pre-trained language model.

Interpreting text-based similarity

Semantic search techniques via focused summarizations are described. For example, a search query is received for a text-based content item in a data set comprising a plurality of text-based content items. A first feature vector representative of the search query is obtained. A respective semantic similarity score is determined between the first feature vector and each of a plurality of second feature vectors. Each of the second feature vectors is representative of a machine-generated summarization of a respective text-based content item. The machine-generated summarization comprises a plurality of multi-word fragments that are selected from the respective text-based content item via a transformer-based machine learning model. A search result is provided responsive to the search query. The search result comprises a subset of the plurality of text-based content items associated with a respective second feature vector having a semantic similarity score that has a predetermined relationship with a predetermined threshold value.

Systems and methods for semantic search via focused summarizations

Systems and methods are provided for optimizing data storage and improving the speed of data retrieval in a data store, such as a storage server connected to a large network through the use of bucketing techniques to create efficient data structures for storing received key-value datasets at one or more storage servers. Fast key-value read requests and key-value retrievals may be accomplished through the use of multiphase lookup operations on the one or more storage servers. The system is optimized for best performance of retrieval through the separation of the write and read mechanisms. Systems and methods provided herein control the level of wastefulness on the back end of a system and reduce read operation inefficiencies on the front end of a system.

Optimized data storage for fast retrieval

Growing community of inventors

Kfar Veradim, Israel

Nir Nice