Abstract: A method and system for generating cluster level explanations for an input data having limited or special values are disclosed. The method includes obtaining an input data set and a clustering stopping criteria, the input data set including multiple features, and each of the features having multiple feature values; performing features decomposition on the input data; performing correlation analysis based on the features decomposition and a correlation threshold value; grouping the features having different feature values into multiple clusters; training a model based on the obtained input data; obtaining a target input data to be tested and a number of cores; grouping the number of cores into multiple clusters; and computing explanations at a cluster level.

Abstract: Methods and systems for detecting attempted manipulation of a machine learning model via explanation poisoning are provided. The method includes: computing explanations based on outputs of the model that include information that relates to features that affect the output of the model with respect to the first data point; assigning labels to the explanations based on the features; generating an explanation ensemble that resides in an N-dimensional space, N being equal to a number of assigned labels plus one; determining a region within the N-dimensional space for which a subsequent introduction of data causes a subsequent explanation that does not relate to the features; and when the additional data is introduced to the determined region, generating an alert message for notifying a user that a likelihood of adverse manipulation of the model is high based on the additional data.

Abstract: A method for facilitating automatic identification and automatic remediation of inconsistencies in model explanations is disclosed. The method includes receiving, via an application programming interface, an input that includes training data, test data, and a selected metric; training, by using the input, a model to compute a model performance value that corresponds to the selected metric; determining a first listing of key features for the model based on feature attributions of the model; generating evaluation models based on the first listing to compute a second listing of evaluation values; computing a change value for each of the evaluation values in the second listing to identify inconsistencies; and initiating actions to resolve the identified inconsistencies.

Abstract: A method and system for determining clustering relevance in a volatile data environment and adjusting clustering composition for improved accuracy are disclosed. The method includes plotting a dataset and generating at least one grand truth data value, and clustering the plotted dataset for generating data clusters, in which the clustering is performed based on correlation of individual data values included in the dataset. The method further includes independently training machine learning (ML) algorithm for each of the data clusters for generating a managing ML algorithm for the dataset, applying the managing ML algorithm to the dataset for predicting at least one future data value, and comparing differences between the grand truth data value and the future data value for estimating a clustering error, and adjusting composition of at least one of the plurality of data clusters based on the estimated clustering error.

Abstract: A method for providing explanations of predictive outputs is disclosed. The method includes receiving, via an application programming interface, an input; temporally segmenting the input to generate a finite set of time windows; training machine learning models for each of the time windows; generating, by using each of the trained machine learning models, predictions for a target time based on the input; generating a set of common background data for each of the time windows based on the input; determining respective mode explanations for each of the time windows based on the corresponding set of common background data, the corresponding trained machine learning models, and the corresponding predictions; and determining reconciled explanations for a target prediction that corresponds to the target time based on the input and the respective mode explanations.

Abstract: Methods and systems for using a non-linear machine learning model to generate explanations that relate to decisions made by the model and for repairing such explanations in order to improve quality and accuracy of model outputs are provided. The method includes: receiving a data set that corresponds to attributes that pertain to a decision to be made; inputting the data set to a machine learning model; generating a baseline decision that corresponds to an output of the model with respect to data set; computing, based on the baseline decision, an explanation that relates to at least one of the attributes; estimating one or more errors associated with the explanation; and computing, based on the estimated error(s), at least one repair that corresponds to a modification of the explanation, and a cost for repairing the explanation.

Abstract: A method of semantic object detection in an image dataset includes extracting semantic links relevant to the image dataset. Objects are detected in the image dataset and confidence scores are assigned to the detected objects. The semantic object detection compares the detected objects with the semantic links and augments the confidence scores based on the semantic links between the detected objects.

Abstract: Methods and systems for generating a counterfactual explanation that is robust with respect to a machine learning model and changes in the model are provided. The method includes: receiving raw data and training a model by using the raw data; perturbing the model by modifying the raw data; computing a first counterfactual explanation that relates to the model; computing a first counterfactual stability metric that relates to the original version of the first model and a second counterfactual stability metric that relates to the perturbed version of the first model; retrieving unstable counterfactual factors that relates to original and perturbed versions of the model; deleting data points that include any such unstable counterfactual factor; and reconstructing the model based on data that does not include the deleted data points.

Abstract: A method for identifying causal recourse for explanations of a plurality of models is disclosed. The method includes determining a causal model by using a corresponding causal graph and raw data, the causal graph relating to a description of relationships between covariates; selecting a list of model features from a model that explains a counterfactual outcome; computing causal counterfactual inputs by using the selected list and the determined causal model; generating predictions on causal counterfactuals by using the causal counterfactual inputs and the model; and verifying that the predictions correspond to the counterfactual outcome.

Abstract: Various methods, apparatuses/systems, and media for computing data contraction and similarity from heterogeneous data descriptors are disclosed. A processor computes common features data among a first data point and a second data point by comparing the first data point and the second data point and their respective data distributions; links a pre-computed knowledge graph with the first data point and the second data point; computes, in response to linking, knowledge-comparable features data among the first data point and the second data point based on other features, received as input, that are not common features; computes knowledge-comparable data based on the knowledge-comparable features data and the common features data; computes similarity of the first data point and the second data point based on the knowledge-comparable data; and generates a data contraction map along with assigned similarity score based on the computed similarity.

Abstract: Methods and systems for aligning a logic of a machine learning model with an explanation associated with the model are provided. The method includes: receiving raw data and training a model by using the raw data; determining common background data based on the raw data; determining an inference that indicates a logic of the model; computing a first explanation about the inference based on an output of the model and the common background data; computing a model differentiator that indicates an item that is important to the logic but not to the first explanation; computing an explanation differentiator that indicates an item that is important to the first explanation but not to the logic; computing a distance metric that indicates a degree of similarity between the logic and the first explanation; and computing a second explanation that includes a respective ranking score for each feature that affects the inference.

Abstract: Methods and systems for obtaining contextual information about a machine learning model are provided. The method includes: receiving raw data that is usable for training a model; training the by using the raw data; computing a set of common background data based on the raw data; computing a first explanation based on an output of the model and the set of common background data; computing, based on an output of the model, an agnostic model representation of the model; computing, based on the first explanation and the agnostic model representation, a deep, compact, and dense explanation-driven representation of the model; and determining, based on the explanation-driven representation, contextual information that relates to the model.

Abstract: Methods and systems for detecting attempted manipulation of a machine learning model via explanation poisoning are provided. The method includes: computing explanations based on outputs of the model that include information that relates to features that affect the output of the model with respect to the first data point; assigning labels to the explanations based on the features; generating an explanation ensemble that resides in an N-dimensional space, N being equal to a number of assigned labels plus one; determining a region within the N-dimensional space for which a subsequent introduction of data causes a subsequent explanation that does not relate to the features; and when the additional data is introduced to the determined region, generating an alert message for notifying a user that a likelihood of adverse manipulation of the model is high based on the additional data.

Abstract: A method for facilitating model refinement via evolutive computation for a predetermined characteristic is disclosed. The method includes capturing a model explanation for a model based on a sampled data set, the model explanation including a listing of model features based on feature scores; identifying feature sets based on the model explanation, the feature sets including a selection of the model features based on the listing; computing, by using raw data, projected data sets for each of the feature sets based on the corresponding selection; generating a data set graph based on the projected data sets, the data set graph representing a relationship between each of the projected data sets; selecting, by using the data set graph, the projected data sets; and validating the selected projected data sets based on a corresponding target characteristic value and a corresponding computed characteristic value.

Abstract: Various methods, apparatuses/systems, and media for computing change-agnostic data points are disclosed. A processor trains a machine learning model by using the at least the first set of raw data; computes a set of explanations for all combinations based on output data of the trained machine learning model, the first set of raw data, and sampled raw data computed by applying a sampling algorithm on the raw data; computes a compact representation of the set of explanations corresponding to a pre-configured dimension based on compression quality and generating a set of compressed explanations; computes a unique representation of model explanation with respect to the pre-configured dimension; determines whether the model explanation is robust to changes in data through data perturbation; and computes change-agnostic data points based on determining that the model explanation is robust to changes in data through data perturbation.

Abstract: Various methods, apparatuses/systems, and media for computing strategies for model inferences are disclosed. A processor generates background data from raw data and data sampling strategies associated with a particular security instrument; computes a model for each pair of raw data and machine learning algorithm; computes model explanation for each pair of the background data and the model; normalizes the computed model explanation by utilizing a predefined algorithm; computes a deep dense representation of each explanation based on the normalized explanation of the computed model; clusters the deep dense representation of each explanation; computes a deep dense representation of explanation of each predicted target data version associated with features recovery; compares the deep dense representation of each explanation with the deep dense representation of explanation of each predicted target data version; and computes a strategy of model selection for each target data version as output.

Abstract: There is provided a method and a system for evaluating a relevance score of a given subset of nodes in a knowledge graph (KG) for purpose of link prediction. An ontology used to generate the KG is obtained and clustered to obtain a set of ontology clusters. A set of vectors having been generated by using an embedding model on the KG is obtained and clustered to obtain a set of vector clusters. Training subgraphs are generated based on the set of ontology clusters and the set of vector clusters by removing subsets of nodes from the KG. Respective prediction models are trained on each training subgraph and ranked based on their link predictions. The relevance score of each removed subset of nodes is determined based on the ranked models. A given subset of nodes is provided as a potential explanation based on the relevance score.

Abstract: There is provided a method and system for training an object recognition machine learning model to perform object recognition in data acquired by ultrawide field of view (UW FOV) sensors to thereby obtain a distortion-aware object recognition model. The object recognition model comprises convolution layers each associated with a set of kernels. During training on a UW FOV labelled training dataset, deformable kernels are learned in a manifold space, mapped back to Euclidian space and used to perform convolutions to obtain output feature maps which are used to perform object recognition predictions. Model parameters of the distortion-aware object recognition model may be transferred to other architectures of object recognition models, which may be further compressed for deployment on embedded systems such as electronic devices on board autonomous vehicles.

Abstract: Implementations include providing, by the PKG platform, an initial knowledge graph based on user-specific data associated with a user, and a domain-specific knowledge graph, receiving, by the PKG platform, data representative of at least one answer provided from the user to a respective question, providing, by the PKG platform, an expanded knowledge graph based on the initial knowledge graph, the expanded knowledge graph including one or more nodes and respective edges based on the data, generating, by the PKG platform, a weighted knowledge graph based a groundtruth knowledge graph, and a targeted knowledge graph, the groundtruth knowledge graph including one or more true answers, and the targeted knowledge graph including the at least one answer provided from the user, and generating, by the PKG platform, the hyper-personalized knowledge graph (hpKG) based on the weighted knowledge graph, the hpKG being unique to the user within a domain.

Abstract: A system for predicting the occurrence of an event includes an event detector and a reporting processor. The event detector is configured to: receive data that defines a plurality of social media items; receive a real-time data feed; and predict the occurrence of an event based on a correlation between information in the plurality of social media items and activity associated with the real-time data feed. The reporting processor is configured to determine an event type associated with the event; identify a sentiment of the predicted event based on historical data in the real-time data feed, and generate a recommendation for preventing the occurrence of the event based on at least one of the event type and the sentiment of the predicted event. The recommendation includes a plurality of actions. The reporting processor is coupled to a knowledge graph database that corresponds to an ontology that defines one or more relationships between event types, and response types.