Oracle International Corporation

Yasha Pushak

Sanjay Jinturkar

Tayler Hetherington

Zahra Zohrevand

Nipun Agarwal

Karoon Rashedi Nia

Hassan Chafi

Sungpack Hong

Hesam Fathi Moghadam

Felix Schmidt

Stuart Wray

Robert David Hopkins, Ii

Anatoly Yakovlev

Ali Seyfi

Constantin Le Clei

Fatjon Zogaj

Herein is a universal anomaly threshold based on several labeled datasets and transformation of anomaly scores from one or more anomaly detectors. In an embodiment, a computer meta-learns from each anomaly detection algorithm and each labeled dataset as follows. A respective anomaly detector based on the anomaly detection algorithm is trained based on the dataset. The anomaly detector infers respective anomaly scores for tuples in the dataset. The following are ensured in the anomaly scores from the anomaly detector: i) regularity that an anomaly score of zero cannot indicate an anomaly and ii) normality that an inclusive range of zero to one contains the anomaly scores from the anomaly detector. A respective anomaly threshold is calculated for the anomaly scores from the anomaly detector. After all meta-learning, a universal anomaly threshold is calculated as an average of the anomaly thresholds. An anomaly is detected based on the universal anomaly threshold.

Unify95: meta-learning contamination thresholds from unified anomaly scores

Herein are counterfactual explanations of machine learning (ML) inferencing provided by generative adversarial networks (GANs) that ensure realistic counterfactuals and use latent spaces to optimize perturbations. In an embodiment, a first computer trains a generator model in a GAN. A same or second computer hosts a classifier model that inferences an original label for original feature values respectively for many features. Runtime ML explainability (MLX) occurs on the first or second or a third computer as follows. The generator model from the GAN generates a sequence of revised feature values that are based on noise. The noise is iteratively optimized based on a distance between the original feature values and current revised feature values in the sequence of revised feature values. The classifier model inferences a current label respectively for each counterfactual in the sequence of revised feature values. Satisfactory discovered counterfactuals are promoted as explanations of behavior of the classifier model.

Using generative adversarial networks to construct realistic counterfactual explanations for machine learning models

Herein are techniques for topic modeling and content perturbation that provide machine learning (ML) explainability (MLX) for natural language processing (NLP). A computer hosts an ML model that infers an original inference for each of many text documents that contain many distinct terms. To each text document (TD) is assigned, based on terms in the TD, a topic that contains a subset of the distinct terms. In a perturbed copy of each TD, a perturbed subset of the distinct terms is replaced. For the perturbed copy of each TD, the ML model infers a perturbed inference. For TDs of a topic, the computer detects that a difference between original inferences of the TDs of the topic and perturbed inferences of the TDs of the topic exceeds a threshold. Based on terms in the TDs of the topic, the topic is replaced with multiple, finer-grained new topics. After sufficient topic modeling, a regional explanation of the ML model is generated.

Efficient and accurate regional explanation technique for NLP models

In a computer, each of multiple anomaly detectors infers an anomaly score for each of many tuples. For each tuple, a synthetic label is generated that indicates for each anomaly detector: the anomaly detector, the anomaly score inferred by the anomaly detector for the tuple and, for each of multiple contamination factors, the contamination factor and, based on the contamination factor, a binary class of the anomaly score. For each particular anomaly detector excluding a best anomaly detector, a similarity score is measured for each contamination factor. The similarity score indicates how similar, between the particular anomaly detector and the best anomaly detector, are the binary classes of labels with that contamination factor. For each contamination factor, a combined similarity score is calculated based on the similarity scores for the contamination factor. Based on a contamination factor that has the highest combined similarity score, the computer detects that an additional anomaly detector is inaccurate.

Expert-optimal correlation: contamination factor identification for unsupervised anomaly detection

Techniques are described that extend supervised machine-learning algorithms for use with semi-supervised training. Random labels are assigned to unlabeled training data, and the data is split into k partitions. During a label-training iteration, each of these k partitions is combined with the labeled training data, and the combination is used train a single instance of the machine-learning model. Each of these trained models are then used to predict labels for data points in the k−1 partitions of previously-unlabeled training data that were not used to train of the model. Thus, every data point in the previously-unlabeled training data obtains k−1 predicted labels. For each data point, these labels are aggregated to obtain a composite label prediction for the data point. After the labels are determined via one or more label-training iterations, a machine-learning model is trained on data with the resulting composite label predictions and on the labeled data set.

Generalized expectation maximization for semi-supervised learning

The present invention relates to machine learning (ML) explainability (MLX). Herein are local explanation techniques for black box ML models based on coalitions of features in a dataset. In an embodiment, a computer receives a request to generate a local explanation of which coalitions of features caused an anomaly detector to detect an anomaly. During unsupervised generation of a new coalition, a first feature is randomly selected from features in a dataset. Which additional features in the dataset can join the coalition, because they have mutual information with the first feature that exceeds a threshold, is detected. For each feature that is not in the coalition, values of the feature are permuted in imperfect copies of original tuples in the dataset. An average anomaly score of the imperfect copies is measured. Based on the average anomaly score of the imperfect copies, a local explanation is generated that references (e.g. defines) the coalition.

Fast and accurate anomaly detection explanations with forward-backward feature importance

A model-agnostic global explainer for textual data processing (NLP) machine learning (ML) models, 'NLP-MLX', is described herein. NLP-MLX explains global behavior of arbitrary NLP ML models by identifying globally-important tokens within a textual dataset containing text data. NLP-MLX accommodates any arbitrary combination of training dataset pre-processing operations used by the NLP ML model. NLP-MLX includes four main stages. A Text Analysis stage converts text in documents of a target dataset into tokens. A Token Extraction stage uses pre-processing techniques to efficiently pre-filter the complete list of tokens into a smaller set of candidate important tokens. A Perturbation Generation stage perturbs tokens within documents of the dataset to help evaluate the effect of different tokens, and combinations of tokens, on the model's predictions. Finally, a Token Evaluation stage uses the ML model and perturbed documents to evaluate the impact of each candidate token relative to predictions for the original documents.

Global, model-agnostic machine learning explanation technique for textual data

Techniques are described for fast approximate conditional sampling by randomly sampling a dataset and then performing a nearest neighbor search on the pre-sampled dataset to reduce the data over which the nearest neighbor search must be performed and, according to an embodiment, to effectively reduce the number of nearest neighbors that are to be found within the random sample. Furthermore, KD-Tree-based stratified sampling is used to generate a representative sample of a dataset. KD-Tree-based stratified sampling may be used to identify the random sample for fast approximate conditional sampling, which reduces variance in the resulting data sample. As such, using KD-Tree-based stratified sampling to generate the random sample for fast approximate conditional sampling ensures that any nearest neighbor selected, for a target data instance, from the random sample is likely to be among the nearest neighbors of the target data instance within the unsampled dataset.

Growing community of inventors

Vancouver, Canada

Yasha Pushak