Graph representation learning serves as the core of important prediction tasks, ranging from product recommendation to fraud detection.
Compliments and concerns in reviews are valuable for understanding users' shopping interests and their opinions with respect to specific aspects of certain items.
Recent multilingual pre-trained language models have achieved remarkable zero-shot performance, where the model is only finetuned on one source language and directly evaluated on target languages.
Next, a dual discriminator based adversarial training procedure, which jointly considers an image discriminator that can maintain the local consistency at frame-level and a video discriminator that can enforce the global coherence of temporal dynamics, is employed to enhance the future frame prediction.
Measuring document similarity plays an important role in natural language processing tasks.
Motivated by the success of disentangled representation learning in computer vision, we study the possibility of learning semantic-rich time-series representations, which remains unexplored due to three main challenges: 1) sequential data structure introduces complex temporal correlations and makes the latent representations hard to interpret, 2) sequential models suffer from KL vanishing problem, and 3) interpretable semantic concepts for time-series often rely on multiple factors instead of individuals.
Moreover, we observe that open-set face recognition systems are more vulnerable than closed-set systems under different types of attacks.
We present a contrasting learning approach with data augmentation techniques to learn document representations in an unsupervised manner.
Forecasting on sparse multivariate time series (MTS) aims to model the predictors of future values of time series given their incomplete past, which is important for many emerging applications.
As texts always contain a large proportion of task-irrelevant words, accurate alignment between aspects and their sentimental descriptions is the most crucial and challenging step.
Graph Neural Networks (GNNs) have shown to be powerful tools for graph analytics.
The unique explanation interpreting each instance independently is not sufficient to provide a global understanding of the learned GNN model, leading to a lack of generalizability and hindering it from being used in the inductive setting.
Accurate air turbulence forecasting can help airlines avoid hazardous turbulence, guide the routes that keep passengers safe, maximize efficiency, and reduce costs.
Pre-trained language models such as BERT have achieved great success in a broad range of natural language processing tasks.
To address these challenges, in this paper, we propose OC4Seq, a multi-scale one-class recurrent neural network for detecting anomalies in discrete event sequences.
We introduce SIGL, a new tool for detecting malicious behavior during software installation.
Outlier detection is an important data mining task with numerous practical applications such as intrusion detection, credit card fraud detection, and video surveillance.
Detecting anomalies in dynamic graphs is a vital task, with numerous practical applications in areas such as security, finance, and social media.
Inductive and unsupervised graph learning is a critical technique for predictive or information retrieval tasks where label information is difficult to obtain.
For this problem, existing approaches, with shallow or deep architectures, have three major drawbacks.
In practice, however, these two sets of reviews are notably different: users' reviews reflect a variety of items that they have bought and are hence very heterogeneous in their topics, while an item's reviews pertain only to that single item and are thus topically homogeneous.
Information systems have widely been the target of malware attacks.
Graph representation learning, aiming to learn low-dimensional representations which capture the geometric dependencies between nodes in the original graph, has gained increasing popularity in a variety of graph analysis tasks, including node classification and link prediction.
How to address the vulnerabilities and defense GNN against the adversarial attacks?
The key idea is to leverage the representation learning of the heterogeneous program behavior graph to guide the reidentification process.
Subsequently, given the signature matrices, a convolutional encoder is employed to encode the inter-sensor (time series) correlations and an attention based Convolutional Long-Short Term Memory (ConvLSTM) network is developed to capture the temporal patterns.
The problem of network representation learning, also known as network embedding, arises in many machine learning tasks assuming that there exist a small number of variabilities in the vertex representations which can capture the "semantics" of the original network structure.
In this paper, we present a Deep Autoencoding Gaussian Mixture Model (DAGMM) for unsupervised anomaly detection.
The Nonlinear autoregressive exogenous (NARX) model, which predicts the current value of a time series based upon its previous values as well as the current and past values of multiple driving (exogenous) series, has been studied for decades.
Time series forecasting for streaming data plays an important role in many real applications, ranging from IoT systems, cyber-networks, to industrial systems and healthcare.
Structures and evolutions of the invariance network, in particular the vanishing correlations, can shed important light on locating causal anomalies and performing diagnosis.