International Business Machines Corporation

Massachusetts Institute of Technology

Dakuo Wang

Chuang Gan

Ming Tan

Bo Wu

Yang Zhang

Haoyu Wang

Sijia Liu

Mo Yu

Gregory Bramble

Abel Nicolas Valente

Arunima Chaudhary

Jing James Xu

Bei Chen

Ji Hui Yang

Horst Cornelius Samulowitz

Daniel Karl I Weidele

Si Er Han

Zhenfang Chen

Lingfei Wu

Peter Daniel Kirchner

Dhavalkumar C Patel

Syed Yousaf Shah

Qian Pan

Jun Song Wang

Saloni Potdar

Jun Wang

Shiyu Chang

Long H Vu

Saket Sathe

Xuan-Hong Dang

Parikshit Ram

Lin Ju

John Dillon Eversman

Voranouth Supadulya

Yi Wang

Xuye Liu

Xin Ru Wang

James Johnson

Quanfu Fan

Theodoros Salonidis

Xue Ying Zhang

Petros Zerfos

Lisa Amini

Pin-Yu Chen

Lei Yu

Yufang Hou

Wesley M Gifford

Chen Wang

Yang Yu

Yunfeng Zhang

Tengfei Ma

Rameswar Panda

Antonio Jose Jimeno Yepes

Xiaoxiao Guo

Deepak Vijaykeerthy

Vaibhav Saxena

Udayan Khurana

Subhro Das

Alexander Gray

Kaizhi Qian

Alex Swain

Jason Tsay

Long Vu

Yupeng Gao

Zahra Ashktorab

Gregory Filla

Carolina Maria Spina

Dongyu Liu

Yi Sun

Edward Sun

Nicholas Mazzitelli

A computer-implemented method for visual question generation includes training an alignment module to analyze an image, an answer hint, and a visual hint with respect to the image. A k-nearest neighbors (KNN) graph is constructed by performing an aligned embedding for each region of the image. A node embedding component is generated by using a graph embedding component of the KNN graph. A visual question is generated by sequence decoding each image and graph of the image.

Visual question generation with answer-awareness and region-reference

A dataset including features and values associated with the features can be received. Each of the features in the dataset can be mapped to a corresponding node in a knowledge graph based on the concept represented by the corresponding node. The knowledge graph can be traversed to find a candidate node connected to at least one mapped node, the candidate node not being mapped to a feature in the dataset. A concept associated with the candidate node can be identified as a new feature. A machine learning model pipeline can use the features in the dataset and the new feature to select a subset of features for training a machine learning model.

Interactive feature engineering in automatic machine learning with domain knowledge

According to one embodiment, a method, computer system, and computer program product for identifying one or more intrinsic physical properties of one or more objects is provided. The present invention may include identifying one or more objects in a video set, extracting observable physical properties of the identified one or more objects from the video set, including one or more trajectories, and inferring, by a property-based graph neural network, intrinsic properties of the one or more objects based on the trajectories.

Object-centric and relation-centric graph neural networks for physical property discovery

The exemplary embodiments disclose a method, a computer program product, and a computer system for determining that one or more model pipelines satisfy one or more constraints. The exemplary embodiments may include detecting a user uploading data, one or more constraints, and one or more model pipelines, collecting the data, the one or more constraints, and the one or more model pipelines, and determining that one or more of the model pipelines satisfies all of the one or more constraints based on applying one or more algorithms to the collected data, constraints, and model pipelines.

Machine learning with multiple constraints

Use a computerized trained graph neural network model to classify an input instance with a predicted label. With a computerized graph neural network interpretation module, compute a gradient-based saliency matrix based on the input instance and the predicted label, by taking a partial derivative of class prediction with respect to an adjacency matrix of the model. With a computerized user interface, obtain user input responsive to the gradient-based saliency matrix. Optionally, modify the trained graph neural network model based on the user input; and re-classify the input instance with a new predicted label based on the modified trained graph neural network model.

Interpretable visualization system for graph neural network

Mechanisms are provided for performing artificial intelligence-based video question answering. A video parser parses an input video data sequence to generate situation data structure(s), each situation data structure comprising data elements corresponding to entities, and first relationships between entities, identified by the video parser as present in images of the input video data sequence. First machine learning computer model(s) operate on the situation data structure(s) to predict second relationship(s) between the situation data structure(s). Second machine learning computer model(s) execute on a received input question to predict an executable program to execute to answer the received question. The program is executed on the situation data structure(s) and predicted second relationship(s). An answer to the question is output based on results of executing the program.

Neural-symbolic action transformers for video question answering

A vehicle light signal detection and recognition method, system, and computer program product include bounding, using a coarse attention module, one or more regions of an image of an automobile including at least one of a brake light and a signal light generated by automobile signals which include illuminated sections to generate one or more bounded region, removing, using a fine attention module, noise from the one or more bounded regions to generate one or more noise-free bounded regions, and identifying the at least one of the brake light and the signal light from the one or more noise-free bounded regions.

Coarse-to-fine attention networks for light signal detection and recognition

A processor may receive a video including a plurality of video frames in sequence and a question regarding the video. For a video frame in the plurality of video frames, a processor may parse the video frame into objects and relationships between the objects, and create a subgraph of nodes representing objects and edges representing the relationships, where parsing and creating are performed for each video frame in the plurality of video frames, where a plurality of subgraphs can be created. A processor may create a hypergraph connecting subgraphs by learning relationships between the nodes of the subgraphs, where a hyper-edge is created to represent a relationship between at least one node of one subgraph and at least one node of another subgraph in the plurality of subgraphs. A processor may generate an answer to the question based on the hypergraph.

Transformers for real world video question answering

Techniques regarding transferring learning outcomes across machine learning tasks in automated machine learning systems are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a transfer learning component that can executes a machine learning task using an existing artificial intelligence model on a sample dataset based on a similarity between the sample dataset and a historical dataset. The existing artificial intelligence model can be generated by automated machine learning and trained on the historical dataset.

Transfer learning across automated machine learning systems

One or more computer processors improve action recognition by removing inference introduced by visual appearances of objects within a received video segment. The one or more computer processors extract appearance information and structure information from a received video segment. The one or more computer processors calculate a factual inference (TE) for the received video segment utilizing the extracted appearance information and structure information. The one or more computer processors calculate a counterfactual debiasing inference (NDE) for the received video segment. The one or more computer processors calculate a total indirect effect (TIE) by subtracting the calculated counterfactual debiased inference from the calculated factual inference. The one or more computer processors action recognize the received video segment by selecting a classification result associated with a highest calculated TIE.

Counterfactual debiasing inference for compositional action recognition

An artificial intelligence (AI) interaction method, system, and computer program product include selecting an artificial intelligence model to respond to a query to generating a response to the query using the selected artificial intelligence model, and receiving the response to the query from the selected artificial intelligence model.

Natural language interaction with automated machine learning systems

To automate time series forecasting machine learning pipeline generation, a data allocation size of time series data may be determined based on one or more characteristics of a time series data set. The time series data may be allocated for use by candidate machine learning pipelines based on the data allocation size. Features for the time series data may be determined and cached by the candidate machine learning pipelines. Predictions of each of the candidate machine learning pipelines using at least the one or more features may be evaluated. A ranked list of machine learning pipelines may be automatically generated from the candidate machine learning pipelines for time series forecasting based upon evaluating predictions of each of the one or more candidate machine learning pipelines.

Automated time series forecasting pipeline generation

Obtain, at a computing device, a segment of computer code. With a classification module of a machine learning system executing on the computing device, determine a required annotation category for the segment of computer code. With an annotation generation module of the machine learning system executing on the computing device, generate a natural language annotation of the segment of computer code based on the segment of computer code and the required annotation category. Provide the natural language annotation to a user interface for display adjacent the segment of computer code.

Learning-based automated machine learning code annotation with graph neural network

An embodiment of the invention may include a method, computer program product, and system for creating a data analysis tool. The method may include a computing device that generates an AI pipeline based on an input dataset, wherein the AI pipeline is generated using an Automated Machine Learning program. The method may include converting the AI pipeline to a non-native format of the Automated Machine Learning program. This may enable the AI pipeline to be used outside of the Automated Machine Learning program, thereby increasing the usefulness of the created program by not tying it to the Automated Machine Learning program. Additionally, this may increase the efficiency of running the AI pipeline by eliminating unnecessary computations performed by the Automated Machine Learning program.

Code generation for Auto-AI

A bi-directional spatial-temporal transformer neural network (BDSTT) is trained to predict original coordinates of a skeletal joint in a specific frame through relative relationships of the skeletal joint to other joints and to the state of the skeletal joint in other frames. Obtain a plurality of frames comprising coordinates of the skeletal joint and coordinates of other joints. Produce a spatially masked frame by masking the original coordinates of the skeletal joint. Provide the specific frame, the spatially masked frame, and at least one more frame to a coordinate prediction head of the BDSTT. Obtain, from the coordinate prediction head, a prediction of coordinates for the skeletal joint. Adjust parameters of the BDSTT until a mean-squared error, between the prediction of coordinates for the skeletal joint and the original coordinates of the skeletal joint, converges.

Skeleton-based action recognition using bi-directional spatial-temporal transformer

Growing community of inventors

Cambridge, MA, United States of America

Dakuo Wang