Search Results for author:
Found 18 papers, 7 papers with code
Automated Contrastive Learning Strategy Search for Time Series
In this paper, we present an Automated Machine Learning (AutoML) practice at Microsoft, which automatically learns CLS for time series datasets and tasks, namely Automated Contrastive Learning (AutoCL).
Causality-Aware Spatiotemporal Graph Neural Networks for Spatiotemporal Time Series Imputation
In this paper, we first revisit spatiotemporal time series imputation from a causal perspective and show how to block the confounders via the frontdoor adjustment.
Mastering Long-Tail Complexity on Graphs: Characterization, Learning, and Generalization
To bridge this gap, we propose a generalization bound for long-tail classification on graphs by formulating the problem in the fashion of multi-task learning, i. e., each task corresponds to the prediction of one particular class.
STERLING: Synergistic Representation Learning on Bipartite Graphs
Most recent bipartite graph SSL methods are based on contrastive learning which learns embeddings by discriminating positive and negative node pairs.
Retrieval Based Time Series Forecasting
In this paper, we show both theoretically and empirically that the uncertainty could be effectively reduced by retrieving relevant time series as references.
ARIEL: Adversarial Graph Contrastive Learning
In this work, by introducing an adversarial graph view for data augmentation, we propose a simple but effective method, Adversarial Graph Contrastive Learning (ARIEL), to extract informative contrastive samples within reasonable constraints.
COIN: Co-Cluster Infomax for Bipartite Graphs
We theoretically prove that COIN is able to effectively increase the mutual information of node embeddings and COIN is upper-bounded by the prior distributions of nodes.
Adversarial Graph Contrastive Learning with Information Regularization
Contrastive learning is an effective unsupervised method in graph representation learning.
Graph Communal Contrastive Learning
We argue that the community information should be considered to identify node pairs in the same communities, where the nodes insides are semantically similar.
X-GOAL: Multiplex Heterogeneous Graph Prototypical Contrastive Learning
X-GOAL is comprised of two components: the GOAL framework, which learns node embeddings for each homogeneous graph layer, and an alignment regularization, which jointly models different layers by aligning layer-specific node embeddings.
Multiplex Graph Neural Network for Extractive Text Summarization
Extractive text summarization aims at extracting the most representative sentences from a given document as its summary.
Network of Tensor Time Series
We propose a novel model called Network of Tensor Time Series, which is comprised of two modules, including Tensor Graph Convolutional Network (TGCN) and Tensor Recurrent Neural Network (TRNN).
HDMI: High-order Deep Multiplex Infomax
To address the above-mentioned problems, we propose a novel framework, called High-order Deep Multiplex Infomax (HDMI), for learning node embedding on multiplex networks in a self-supervised way.
SODA: Detecting Covid-19 in Chest X-rays with Semi-supervised Open Set Domain Adaptation
However, direct transfer across datasets from different domains may lead to poor performance for CNN due to two issues, the large domain shift present in the biomedical imaging datasets and the extremely small scale of the COVID-19 chest x-ray dataset.
Show, Describe and Conclude: On Exploiting the Structure Information of Chest X-Ray Reports
In this work, we propose a novel framework that exploits the structure information between and within report sections for generating CXR imaging reports.
Adversarial Domain Adaptation Being Aware of Class Relationships
In this paper, we propose a novel relationship-aware adversarial domain adaptation (RADA) algorithm, which first utilizes a single multi-class domain discriminator to enforce the learning of inter-class dependency structure during domain-adversarial training and then aligns this structure with the inter-class dependencies that are characterized from training the label predictor on source domain.
Cross-Domain Labeled LDA for Cross-Domain Text Classification
To this end, we embed the group alignment and a partial supervision into a cross-domain topic model, and propose a Cross-Domain Labeled LDA (CDL-LDA).
On the Automatic Generation of Medical Imaging Reports
To cope with these challenges, we (1) build a multi-task learning framework which jointly performs the pre- diction of tags and the generation of para- graphs, (2) propose a co-attention mechanism to localize regions containing abnormalities and generate narrations for them, (3) develop a hierarchical LSTM model to generate long paragraphs.
