Abstract: A solution arranged to build or train a machine learning model (ML model) that can be uploaded to a server arranged to deploy the ML model to communicating devices. The ML model builder can build the ML model and a ML production pipeline. The ML production pipeline can train the ML model, convert the ML model to a web browser compatible format, and upload the converted ML model to the server. The ML model can receive as input a sequence of prior activities on one communicating device in the communicating devices, analyze the sequence of prior activities on the communicating device, predict a next activity on the communicating device based on the analysis of the sequence of prior activities, preemptively search a computer network based on the predicted next activity to find a computer asset, and preload the found computer asset to a storage in the communicating device.

Abstract: Systems and methods for prompt tuning can utilize previously-learned prompts for the initialization of tuning for prompts on different tasks that may differ from the task associated with the previously-learned prompt. The prompt being utilized for initialization can be a generic prompt and/or may be a prompt selected based on a determined similarity between two or more task embeddings.

Abstract: Methods, systems, and apparatus for generating trajectory predictions for one or more target agents. In one aspect, a system comprises one or more computers configured to obtain scene context data characterizing a scene in an environment at a current time point, where the scene includes multiple agents that include a target agent and one or more context agents, and the scene context data includes respective context data for each of multiple different modalities of context data. The one or more computers then generate an encoded representation of the scene in the environment that includes one or more embeddings and process the encoded representation of the scene context data using a decoder neural network to generate a trajectory prediction output for the target agent that predicts a future trajectory of the target after the current time point.

Abstract: The present disclosure provides computing systems and methods directed to algorithms and the underlying machine learning (ML) models for evaluating similarity between graphs using graph structures and/or attributes. The systems and methods disclosed may provide advantages or improvements for comparing graphs without additional context or input from a person (e.g., the methods are unsupervised). In particular, the systems and methods of the present disclosure can operate to generate respective embeddings for one or more target graphs, where the embedding for each target graph is indicative of a respective similarity of such target graph to each of a set of source graphs, and where a pair of embeddings for a pair of target graphs can be used to assess a similarity between the pair of target graphs.

Abstract: Systems and methods for natural language processing can leverage trained prompts to condition a large pre-trained machine-learned model to generate an output for a specific task. For example, a subset of parameters may be trained for the particular task to then be input with a set of input data into the pre-trained machine-learned model to generate the task-specific output. During the training of the prompt, the parameters of the pre-trained machine-learned model can be frozen, which can reduce the computational resources used during training while still leveraging the previously learned data from the pre-trained machine-learned model.

Abstract: A solution arranged to build or train a machine learning model and to upload the machine learning model to a server arranged to deploy the machine learning model to a plurality of communicating devices. The solution can include a machine learning model builder arranged to build the machine learning model and a machine learning production pipeline. The machine learning production pipeline can be arranged to train the machine learning model, convert the machine learning model to a web browser compatible format, and upload the converted machine learning model to the server.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for a graph processing system. In one aspect, the graph processing system obtains data identifying a first node and a second node from a graph of nodes and edges. The system processes numeric embeddings of the first node and the second node using a manifold neural network to generate respective manifold coordinates of the first node and the second node. The system applies a learned edge function to the manifold coordinates of the first node and the manifold coordinates of the second node to generate an edge score that represents a likelihood that an entity represented by the first node and an entity represented by the second node have a particular relationship.

Abstract: Systems, methods, and computer readable media related to determining one or more responses to provide that are responsive to an electronic communication that is generated through interaction with a client computing device. For example, determining one or more responses to provide for presentation to a user as suggestions for inclusion in a reply to an electronic communication sent to the user. Some implementations are related to training and/or using separate input and response neural network models for determining responses for electronic communications. The input neural network model and the response neural network model can be separate, but trained and/or used cooperatively.

Abstract: Systems, methods, and computer readable media related to information retrieval. Some implementations are related to training and/or using a relevance model for information retrieval. The relevance model includes an input neural network model and a subsequent content neural network model. The input neural network model and the subsequent content neural network model can be separate, but trained and/or used cooperatively. The input neural network model and the subsequent content neural network model can be “separate” in that separate inputs are applied to the neural network models, and each of the neural network models is used to generate its own feature vector based on its applied input. A comparison of the feature vectors generated based on the separate network models can then be performed, where the comparison indicates relevance of the input applied to the input neural network model to the separate input applied to the subsequent content neural network model.

Abstract: Systems, methods, and computer readable media related to information retrieval. Some implementations are related to training and/or using a relevance model for information retrieval. The relevance model includes an input neural network model and a subsequent content neural network model. The input neural network model and the subsequent content neural network model can be separate, but trained and/or used cooperatively. The input neural network model and the subsequent content neural network model can be “separate” in that separate inputs are applied to the neural network models, and each of the neural network models is used to generate its own feature vector based on its applied input. A comparison of the feature vectors generated based on the separate network models can then be performed, where the comparison indicates relevance of the input applied to the input neural network model to the separate input applied to the subsequent content neural network model.

Abstract: The present disclosure provides computing systems and methods directed to algorithms and the underlying machine learning (ML) models for evaluating similarity between graphs using graph structures and/or attributes. The systems and methods disclosed may provide advantages or improvements for comparing graphs without additional context or input from a person (e.g., the methods are unsupervised). In particular, the systems and methods of the present disclosure can operate to generate respective embeddings for one or more target graphs, where the embedding for each target graph is indicative of a respective similarity of such target graph to each of a set of source graphs, and where a pair of embeddings for a pair of target graphs can be used to assess a similarity between the pair of target graphs.

Abstract: Systems, methods, and computer readable media related to information retrieval. Some implementations are related to training and/or using a relevance model for information retrieval. The relevance model includes an input neural network model and a subsequent content neural network model. The input neural network model and the subsequent content neural network model can be separate, but trained and/or used cooperatively. The input neural network model and the subsequent content neural network model can be “separate” in that separate inputs are applied to the neural network models, and each of the neural network models is used to generate its own feature vector based on its applied input. A comparison of the feature vectors generated based on the separate network models can then be performed, where the comparison indicates relevance of the input applied to the input neural network model to the separate input applied to the subsequent content neural network model.

Abstract: Systems, methods, and computer readable media related to determining one or more responses to provide that are responsive to an electronic communication that is generated through interaction with a client computing device. For example, determining one or more responses to provide for presentation to a user as suggestions for inclusion in a reply to an electronic communication sent to the user. Some implementations are related to training and/or using separate input and response neural network models for determining responses for electronic communications. The input neural network model and the response neural network model can be separate, but trained and/or used cooperatively.

Abstract: Methods and apparatus related to determining coreference resolution using distributed word representations. Distributed word representations, indicative of syntactic and semantic features, may be identified for one or more noun phrases. For each of the one or more noun phrases, a referring feature representation and an antecedent feature representation may be determined, where the referring feature representation includes the distributed word representation, and the antecedent feature representation includes the distributed word representation augmented by one or more antecedent features. In some implementations the referring feature representation may be augmented by one or more referring features. Coreference embeddings of the referring and antecedent feature representations of the one or more noun phrases may be learned. Distance measures between two noun phrases may be determined based on the coreference embeddings.