Abstract: Systems and methods for implementing dynamic graph analysis (DGA) to detect anomalous network traffic are provided. The method includes processing communications and profile data associated with multiple devices to determine dynamic graphs. The method includes generating features to model temporal behaviors of network traffic generated by the multiple devices based on the dynamic graphs. The method also includes formulating a list of prediction results for sources of the anomalous network traffic from the multiple devices based on the temporal behaviors.

Abstract: Systems and methods are provided for detail matching. The method includes training a feature classifier to identify technical features, and training a neural network model for a trained importance calculator to calculate an importance value for each identified technical feature. The method further includes receiving a specification sheet including a plurality of technical features, and receiving a plurality of descriptive sheets each including a plurality of technical features. The method further includes identifying the technical features in the specification sheet and the plurality of descriptive sheets using the trained feature classifier, and calculating an importance for each identified technical feature using the trained feature importance calculator.

Abstract: A method for detecting business intent from a business intent corpus by employing an Intent Detection via Multi-hop Unified Syntactic Graph (IDMG) is presented. The method includes parsing each text sample representing a business need description to extract syntactic information including at least tokens and words, tokenizing the words of the syntactic information to generate sub-words for each of the words by employing a multi-lingual pre-trained language model, aligning the generated sub-words to the tokens of the syntactic information to match ground-truth intent actions and objects to the tokenized sub-words, generating a unified syntactic graph, encoding, via a multi-hop unified syntactic graph encoder, the unified syntactic graph to generate an output, and predicting an intent action and object from the output.

Abstract: Methods and systems for embedding a network in a latent space include generating a representation of an input network graph in the latent space using an autoencoder model and generating a representation of a set of noise samples in the latent space using a generator model. A discriminator model discriminates between the representation of the input network graph and the representation of the set of noise samples. The autoencoder model, the generator model, and the discriminator model are jointly trained by minimizing a joint loss function that includes parameters for each model. A final representation of the input network graph is generated using the trained autoencoder model.

Abstract: A method for performing dialysis event prediction by employing a meta-training strategy for model personalization includes, in a meta-training stage, generating segments from temporal records of patient dialysis data, generating, from the segments, a support set and a query set for each patient of a plurality of patients, formulating tasks for each patient in a pre-training set defined as a meta-training framework (M-DCCN), where each task includes the support set and the query set, and sending the tasks to a two-level meta-training algorithm supported training coordinator. The method further includes, in a finetuning stage, sending the M-DCCN to local machines where a finetuning dataset is collected for new patients, the finetuning dataset including a limited amount of data pertaining the new patients, fine-tuning the M-DCCN for personalization, and using the fine-tuned M-DCCN for future predictive dialysis analysis of future new patients by generating prognostic predictive scores.

Abstract: Methods and systems for training a neural network include training models for respective sensor groups in a cyber-physical system. Combinations of sensor groups and operational modes are sampled. A combination model is trained for each of the sampled combinations. A best combination model is determined based on performance measured during training. The best combination model is fine-tuned.

Abstract: Systems and methods for predicting an occurrence of a medical event for a patient using a trained neural network. Historical patient data is preprocessed to generate normalized training samples, and the normalized training samples are sent to a personalized deep convolutional neural network for model pretraining and updating of model parameters. The pretrained model is stored in a remote server for utilization by a local machine for personalization during a preparation time period for a medical treatment. A normalized finetuning set is generated as output, and the model parameters are iteratively finetuned. A personal prediction score for future medical events is generated, and an operation of a medical treatment device is controlled responsive to the prediction score.

Abstract: The present invention provides a press-fitting pipe connector with a toothed ring, including a pipe joint, a sealing ring, a toothed clamping ring, a bushing and a pipe. The pipe joint is a “-”-like round pipe with equal wall thickness, the sealing ring, the toothed clamping ring, and the bushing are assembled in an inner cavity of the pipe joint, a fitting end of the pipe joint is run through inner cavities of the bushing, the toothed clamping ring and the sealing ring in sequence, a radial pressure is applied using a press-fitting tool along an outer diameter of the pipe joint, and both ends of the pipe joint are squeezed from a pipe shape into a neck shape under the action of the pressure. Therefore, the strength index and the safety requirements of the gas, fire-fighting and heat supply pipes of the high-rise buildings can be satisfied.

Abstract: A method for explaining sensor time series data in natural language is presented. The method includes training a neural network model with text-annotated time series data, the neural network model including a time series encoder and a text generator, allowing a human operator to select a time series segment from the text-annotated time series data, the time series segment processed by the time series encoder, outputting, from the time series encoder, a sequence of hidden state vectors, one for each timestep, and generating readable explanatory texts for the human operator based on the selected time series segment, the readable explanatory texts being a set of comment texts explaining and interpreting the selected time series segment in a plurality of different ways.

Abstract: Methods and systems for training a model include training a feature extraction model to extract a feature vector from a multivariate time series segment, based on a set of training data corresponding to measurements of a system in a first domain. Adapting the feature extraction model to a second domain, based on prototypes of the training data in the first domain and new time series data corresponding to measurements of the system in a second domain.

Abstract: Systems and methods for implementing a spatial and temporal attention-based gated recurrent unit (GRU) for node classification over temporal attributed graphs are provided. The method includes computing, using a GRU, embeddings of nodes at different snapshots. The method includes performing weighted sum pooling of neighborhood nodes for each node. The method further includes concatenating feature vectors for each node. Final temporal network embedding vectors are generated based on the feature vectors for each node. The method also includes applying a classification model based on the final temporal network embedding vectors to the plurality of nodes to determine temporal attributed graphs with classified nodes.

Abstract: Systems and methods for a provenance based threat detection tool that builds a provenance graph including a plurality of paths using a processor device from provenance data obtained from one or more computer systems and/or networks; samples the provenance graph to form a plurality of linear sample paths, and calculates a regularity score for each of the plurality of linear sample paths using a processor device; selects a subset of linear sample paths from the plurality of linear sample paths based on the regularity score, and embeds each of the subset of linear sample paths by converting each of the subset of linear sample paths into a numerical vector using a processor device; detects anomalies in the embedded paths to identify malicious process activities, and terminates a process related to the embedded path having the identified malicious process activities.

Abstract: A system is provided for interpretable viewing interest. A transformer with multi-head self-attention derives different hierarchical orders of input features. Hierarchical attention layers (i) aggregate the different hierarchical orders to obtain aggregated single-order feature representations and (iii) derive aggregation attention weights for the different hierarchical orders based on an applied order of the hierarchical attention layers. An attentional scoring layer evaluates the aggregated representations to output a significance of each order with respect to various CTR predictions. A hierarchical interpretation layer determines a respective importance of each input feature in various combinations from which the various CTR predictions are derived based on the aggregation attention weights and the significance of each order.

Abstract: A method for employing a knowledge-driven pre-training framework for learning product representation is presented. The method includes learning contextual semantics of a product domain by a language acquisition stage including a context encoder and two language acquisition tasks, obtaining multi-faceted product knowledge by a knowledge acquisition stage including a knowledge encoder, skeleton attention layers, and three heterogeneous embedding guided knowledge acquisition tasks, generating local product representations defined as knowledge copies (KC) each capturing one facet of the multi-faceted product knowledge, and generating final product representation during a fine-tuning stage by combining all the KCs through a gating network.

Abstract: Compositions and methods are disclosed for producing adeno-associated virus (AAV) in insect cells in vitro. Recombinant baculovirus vectors include an AAV Capsid gene expression cassette (Cap), an AAV Rep gene expression cassette (Rep), and a baculovirus homologous region (hr) located up to about 4 kb from a start codon in an AAV expression cassette. Production levels of baculovirus and AAV in insect cells harboring recombinant baculovirus comprising a Cap, a Rep, and an hr are higher compared to controls comprising a Cap and a Rep but no hr. Furthermore, levels of baculovirus and AAV production in insect cells infected with recombinant baculovirus comprising a Cap, a Rep, and an hr are comparatively stable over serial passages of cells, whereas levels of baculovirus and AAV production decline over serial passages of insect cells comprising recombinant baculovirus comprising a Cap and a Rep, but no hr.

Abstract: Systems and methods for anomaly detection are provided. The method includes structuring a multi-channel spatial-temporal sequence as a four-dimensional array. The method also includes decomposing the four-dimensional array to form a low-rank component representing a background signal and a residual component representing anomalies for each time point of the multi-channel spatial-temporal sequence. The method further includes determining a sequence of anomaly maps by stacking the residual components at all time points together. Anomalies are identified based on the sequence of anomaly maps.

Abstract: A method for employing a deep unsupervised generative approach for disentangled factor learning is presented. The method includes decomposing, via an individual factor disentanglement component, latent variables into independent factors having different semantic meaning, enriching, via a group segment disentanglement component, group-level semantic meaning of sequential data by grouping the sequential data into a batch of segments, and generating hierarchical semantic concepts as interpretable and disentangled representations of time series data.

Abstract: Systems and methods are provided for Cross-lingual Transfer Interpretation (CTI). The method includes receiving text corpus data including premise-hypothesis pairs with a relationship label in a source language, and conducting a source to target language translation. The method further includes performing a feature importance extraction, where an integrated gradient is applied to assign an importance score to each input feature, and performing a cross-lingual feature alignment, where tokens in the source language are aligned with tokens in the target language for both the premise and the hypothesis based on semantic similarity. The method further includes performing a qualitative analysis, where the importance score of each token can be compared between the source language and the target language according to a feature alignment result.

Abstract: Rating prediction systems and methods include extracting aspect-sentiment pairs from an input text. An attention-property-aware rating is estimated for the input text using the extracted aspect-sentiment pairs with a neural network that captures implicit and explicit features of the text. A response to the input text is performed based on the estimated rating.

Abstract: Methods and systems for natural language processing include generating an encoder that includes a global part and a local part, where the global part encodes multi-hop relations between words in an input and where the local part encodes one-hop relations between words in the input. The encoder is trained to form a graph that represents tokens of an input text as nodes and that represents relations between the tokens as edges between the nodes.