Abstract: Surrogate training can include receiving a parameterization of a physical system, where the physical system includes real physical components and the parameterization having corresponding target property in the physical system. The parameterization can be input into a neural network, where the neural network generates a different dimensional parameterization based on the input parameterization. The different dimensional parameterization can be input to a physical model that approximates the physical system. The physical model can be run using the different dimensional parameterization, where the physical model generates an output solution based on the different dimensional parameterization input to the physical model. Based on the output solution and the target property, the neural network can be trained to generate the different dimensional parameterization.

Abstract: Obtain access to a pretrained encoder-decoder language model. Using a dataset including a plurality of text-graph pairs, carry out first fine-tuning training on the pre-trained language model by minimizing cross-entropy loss. A text portion of each text-graph pair includes a list of text tokens and a graph portion of each text-graph pair includes a list of graph tokens. The first fine-tuning training results in an intermediate model. Carry out second fine-tuning training on the intermediate model, by reinforcement learning, to obtain a final model. Make the final model available for deployment.

Abstract: A knowledge graph is constructed as part of a multi-stage process using pretrained language models. Input text in a natural language format is received. In a first stage, a plurality of nodes is generated using a pretrained language model, where the nodes correspond to entities of the input text. In the second stage edges to interconnect the plurality of nodes are generated. The edges are generated responsive to generating each of the plurality of nodes.

Abstract: Embodiments of the invention provide a computer-implemented method that includes applying input representations of a three-dimensional (3D) domain to a generative neural network (GNN); and using the GNN to form a generative model of the 3D domain based at least in part on the input representations. The input representations include a global-shape input representation of the 3D domain.

Abstract: Systems, computer-implemented methods, and computer program products to facilitate a dual learning bridge between text and a knowledge graph are provided. According to an embodiment, a system can comprise a processor that executes computer executable components stored in memory. The computer executable components comprise a model component that employs a model to learn associations between text data and a knowledge graph. The computer executable components further comprise a translation component that uses the model to bidirectionally translate second text data and one or more knowledge graph paths based on the associations.

Abstract: One or more systems, devices, computer program products and/or computer-implemented methods of use provided herein relate to classifying accuracy of analytical model, such as a neural network. A system can comprise a memory that stores computer executable components, and a processor that executes the computer executable components stored in the memory, wherein the computer executable components can comprise an accessing component that accesses an analytical model, a deviation component that generates combined results of the analytical model in response to a set of inputs that vary in degree of perturbation of a set of test data, and an analysis component that compares a range of the combined results to a range of the ideal results.

Abstract: Embodiments of the present invention provide computer-implemented methods, computer program products and computer systems. Embodiments of the present invention can, in response to receiving parameters associated with a problem, train at least one generated data model to evaluate an estimation of a solution for the problem. Embodiments of the present invention can then generate an uncertainty quantification measure associated with an estimation of error for the at least one generated data model.

Abstract: Embodiments relate to a system, program product, and method for inducing creativity in an artificial neural network (ANN) having an encoder and decoder. Neurons are automatically selected and manipulated from one or more layers of the encoder. An encoded vector is sampled for an encoded image. Decoder neurons and a corresponding activation pattern are evaluated with respect to the encoded image. The decoder neurons that correspond to the activation pattern are selected, and an activation setting of the selected decoder neurons is changed. One or more novel data instances are automatically generated from an original latent space of the selectively changed decoder neurons.

Abstract: Techniques for sanitization of machine learning (ML) models are provided. A first ML model is received, along with clean training data. A path is trained between the first ML model and a second ML model using the clean training data. A sanitized ML model is generated based on at least one point on the trained path. One or more ML functionalities are then facilitated using the sanitized ML model.

Abstract: A system and method for designing protein sequences conditioned on a specific target fold. The system is a transformer-based generative framework for modeling a complex sequence-structure relationship. To mitigate the heterogeneity between the sequence domain and the fold domain, a Fold-to-Sequence model jointly learns a sequence embedding using a transformer and a fold embedding from the density of secondary structural elements in 3D voxels. The joint sequence-fold representation through novel intra-domain and cross-domain losses with an intra-domain loss forcing two semantically similar (where the proteins should have the same fold(s)) samples from the same domain to be close to each other in a latent space, while a cross-domain loss forces two semantically similar samples in different domains to be closer. In an embodiment, the Fold-to-Sequence model performs design tasks that include low resolution structures, structures with region of missing residues, and NMR structural ensembles.

Abstract: A computer-implemented method according to one aspect includes training a latent variable model (LVM), utilizing labeled data and unlabeled data within a data set; training a classifier, utilizing the labeled data and associated labels within the data set; and generating new data having a predetermined set of labels, utilizing the trained LVM and the trained classifier.

Abstract: A black box evaluator is accessed and a surrogate machine learning model that provides estimates for the optimization of categorical values for the black box evaluator is generated, the surrogate machine learning model being based upon observations from previous executions of the black box evaluator. The black box evaluator is optimized by selecting, by an acquisition function executing on a computing device, a new candidate point for the categorical values. The black box evaluator is executed with the new candidate point for the categorical values.

Abstract: Generating a drug molecule design by training an attribute predictor model using an embedding of a first molecular data base, training a first machine learning model using the attribute predictor, yielding a second embedding of the first molecular data base, training a binding affinity model using a second molecular database and the second embedding of the first molecular database, and generating a molecule design according to the second embedding and the binding affinity model.

Abstract: Generating a molecule design by training a binding affinity model using a first molecular database and an embedding of a second molecular database and generating a molecule design according to the embedding and the binding affinity model.

Abstract: Techniques for training robust machine learning models for adversarial input data. Training data for a machine learning (ML) model is received. The training data includes a plurality of labels for data elements. First modified training data is generated by modifying one or more of the plurality of labels in the training data using parameterized label smoothing with a first optimization parameter. The ML model is trained using the first modified training data.

Abstract: Systems, computer-implemented methods, and computer program products to facilitate a dual learning bridge between text and a knowledge graph are provided. According to an embodiment, a system can comprise a processor that executes computer executable components stored in memory. The computer executable components comprise a model component that employs a model to learn associations between text data and a knowledge graph. The computer executable components further comprise a translation component that uses the model to bidirectionally translate second text data and one or more knowledge graph paths based on the associations.

Abstract: Aspects of the present invention disclose a method, computer program product, and system for optimizing a result for a combinatorial optimization problem. The method includes one or more processors receiving a black-box model. The method further includes one or more processors learning a multilinear polynomial surrogate model employing an exponential weight update rule. The method further includes one or more processors optimizing the learnt multilinear polynomial surrogate model. The method further includes one or more processors applying the black-box model to the optimized solution found by the multilinear polynomial surrogate model. In an additional aspect, the method of learning an optimized multilinear polynomial surrogate model employing an exponential weight update rule further includes one or more processors calculating utilizing data from the black-box model, an update of the coefficients of the multilinear polynomial surrogate model.

Abstract: Techniques are provided for decentralized parallel min/max optimizations. In one embodiment, the techniques involve generating gradients based on a first set of weights associated with a first node of a neural network, exchanging the first set of weights with a second set of weights associated with a second node, generating an average weight based on the first set of weights and the second set of weights, and updating the first set of weights and the second set of weights via a decentralized parallel optimistic stochastic gradient (DPOSG) algorithm based on the gradients and the average weight.

Abstract: A query-based generic end-to-end molecular optimization (“QMO”) system framework, method and computer program product for optimizing molecules, such as for accelerating drug discovery. The QMO framework decouples representation learning and guided search and applies to any plug-in encoder-decoder with continuous latent representations. QMO framework directly incorporates evaluations based on chemical modeling, analysis packages, and pre-trained machine-learned prediction models for efficient molecule optimization using a query-based guided search method based on zeroth order optimization. The QMO features efficient guided search with molecular property evaluations and constraints obtained using the predictive models and chemical modeling and analysis packages.

Abstract: Run a computerized numerical partial differential equation solver on at least one partial differential equation representing at least one physical constraint of a physical system, to generate a training data set. A true potential corresponds to an exact solution to the at least one partial differential equation. Using a computerized machine learning system, learn, from the training data set, a surrogate of a gradient of the true potential. Using the computerized machine learning system, apply Langevin sampling to the learned surrogate of the gradient, to obtain a plurality of samples corresponding to candidate designs for the physical system. Make the plurality of samples available to a fabrication entity.