Search Results for author:
Found 47 papers, 12 papers with code
Unsupervised Multi-modal Feature Alignment for Time Series Representation Learning
In contrast to conventional methods that fuse features from multiple modalities, our proposed approach simplifies the neural architecture by retaining a single time series encoder, consequently leading to preserved scalability.
Image-Based Soil Organic Carbon Remote Sensing from Satellite Images with Fourier Neural Operator and Structural Similarity
To study the use of CNNs on SOC remote sensing, here we propose the FNO-DenseNet based on the Fourier neural operator (FNO).
FNOSeg3D: Resolution-Robust 3D Image Segmentation with Fourier Neural Operator
Due to the computational complexity of 3D medical image segmentation, training with downsampled images is a common remedy for out-of-memory errors in deep learning.
HartleyMHA: Self-Attention in Frequency Domain for Resolution-Robust and Parameter-Efficient 3D Image Segmentation
With the introduction of Transformers, different attention-based models have been proposed for image segmentation with promising results.
Duet: efficient and scalable hybriD neUral rElation undersTanding
Although both data-driven and hybrid methods are proposed to avoid this problem, most of them suffer from high training and estimation costs, limited scalability, instability, and long-tail distribution problems on high-dimensional tables, which seriously affects the practical application of learned cardinality estimators.
MaxCorrMGNN: A Multi-Graph Neural Network Framework for Generalized Multimodal Fusion of Medical Data for Outcome Prediction
With the emergence of multimodal electronic health records, the evidence for an outcome may be captured across multiple modalities ranging from clinical to imaging and genomic data.
Contrastive Shapelet Learning for Unsupervised Multivariate Time Series Representation Learning
Recent studies have shown great promise in unsupervised representation learning (URL) for multivariate time series, because URL has the capability in learning generalizable representation for many downstream tasks without using inaccessible labels.
TodyNet: Temporal Dynamic Graph Neural Network for Multivariate Time Series Classification
Unfortunately, the existing deep learning-based methods neglect the hidden dependencies in different dimensions and also rarely consider the unique dynamic features of time series, which lack sufficient feature extraction capability to obtain satisfactory classification accuracy.
UniTS: A Universal Time Series Analysis Framework with Self-supervised Representation Learning
Machine learning has emerged as a powerful tool for time series analysis.
DCLP: Neural Architecture Predictor with Curriculum Contrastive Learning
Therefore, the critical issue in utilizing predictors for NAS is to train a high-performance predictor using as few trained neural networks as possible.
FedST: Secure Federated Shapelet Transformation for Time Series Classification
Thus, we design a basic protocol for the FedST kernel that we prove to be secure and accurate.
Fusing Modalities by Multiplexed Graph Neural Networks for Outcome Prediction in Tuberculosis
All these nuances make simple methods of early, late, or intermediate fusion of features inadequate for outcome prediction.
Differentiable Self-Adaptive Learning Rate
Learning rate adaptation is a popular topic in machine learning.
EEML: Ensemble Embedded Meta-learning
To accelerate learning process with few samples, meta-learning resorts to prior knowledge from previous tasks.
FIND:Explainable Framework for Meta-learning
Meta-learning is used to efficiently enable the automatic selection of machine learning models by combining data and prior knowledge.
AutoTS: Automatic Time Series Forecasting Model Design Based on Two-Stage Pruning
We allow the effective combination of design experience from different sources, so as to create an effective search space containing a variety of TSF models to support different TSF tasks.
AutoMC: Automated Model Compression based on Domain Knowledge and Progressive search strategy
Model compression methods can reduce model complexity on the premise of maintaining acceptable performance, and thus promote the application of deep neural networks under resource constrained environments.
TPAD: Identifying Effective Trajectory Predictions Under the Guidance of Trajectory Anomaly Detection Model
They are lack of self-evaluation ability, that is, to examine the rationality of their prediction results, thus failing to guide users to identify high-quality ones from their candidate results.
ATPFL: Automatic Trajectory Prediction Model Design Under Federated Learning Framework
Although the Trajectory Prediction (TP) model has achieved great success in computer vision and robotics fields, its architecture and training scheme design rely on heavy manual work and domain knowledge, which is not friendly to common users.
Addressing Deep Learning Model Uncertainty in Long-Range Climate Forecasting with Late Fusion
Global warming leads to the increase in frequency and intensity of climate extremes that cause tremendous loss of lives and property.
Differentiable Hyper-parameter Optimization
We apply our method for the optimization of various neural network layers' hyper-parameters and compare it with multiple benchmark hyper-parameter optimization models.
Search For Deep Graph Neural Networks
Current GNN-oriented NAS methods focus on the search for different layer aggregate components with shallow and simple architectures, which are limited by the 'over-smooth' problem.
TENSILE: A Tensor granularity dynamic GPU memory scheduling method toward multiple dynamic workloads system
In this paper, we demonstrated TENSILE, a method of managing GPU memory in tensor granularity to reduce the GPU memory peak, considering the multiple dynamic workloads.
FL-AGCNS: Federated Learning Framework for Automatic Graph Convolutional Network Search
Recently, some Neural Architecture Search (NAS) techniques are proposed for the automatic design of Graph Convolutional Network (GCN) architectures.
Approximate Query Processing for Group-By Queries based on Conditional Generative Models
Online sampling chooses samples for the given query at query time, but it requires a long latency.
Auto-STGCN: Autonomous Spatial-Temporal Graph Convolutional Network Search Based on Reinforcement Learning and Existing Research Results
In recent years, many spatial-temporal graph convolutional network (STGCN) models are proposed to deal with the spatial-temporal network data forecasting problem.
EM-RBR: a reinforced framework for knowledge graph completion from reasoning perspective
To solve this problem, in this paper, we propose a general framework, named EM-RBR(embedding and rule-based reasoning), capable of combining the advantages of reasoning based on rules and the state-of-the-art models of embedding.
Automatic Storage Structure Selection for hybrid Workload
Therefore, the users of the database need to select the storage engine and design data model according to the workload encountered.
Auto-CASH: Autonomous Classification Algorithm Selection with Deep Q-Network
In our work, we present Auto-CASH, a pre-trained model based on meta-learning, to solve the CASH problem more efficiently.
Multi-Objective Neural Architecture Search Based on Diverse Structures and Adaptive Recommendation
To reduce searching cost, most NAS algorithms use fixed outer network level structure, and search the repeatable cell structure only.
Index Selection for NoSQL Database with Deep Reinforcement Learning
We propose a new approach of NoSQL database index selection.
Neural Network Segmentation of Cell Ultrastructure Using Incomplete Annotation
The Pancreatic beta cell is an important target in diabetes research.
ConsciousControlFlow(CCF): A Demonstration for conscious Artificial Intelligence
In this demo, we present ConsciousControlFlow(CCF), a prototype system to demonstrate conscious Artificial Intelligence (AI).
LAQP: Learning-based Approximate Query Processing
Querying on big data is a challenging task due to the rapid growth of data amount.
Automatic Hyper-Parameter Optimization Based on Mapping Discovery from Data to Hyper-Parameters
However, most machine learning algorithms are sensitive to the hyper-parameters.
ExperienceThinking: Constrained Hyperparameter Optimization based on Knowledge and Pruning
Motivated by this, we propose ExperienceThinking algorithm to quickly find the best possible hyperparameter configuration of machine learning algorithms within a few configuration evaluations.
Auto-Model: Utilizing Research Papers and HPO Techniques to Deal with the CASH problem
In many fields, a mass of algorithms with completely different hyperparameters have been developed to address the same type of problems.
A General Data Renewal Model for Prediction Algorithms in Industrial Data Analytics
In industrial data analytics, one of the fundamental problems is to utilize the temporal correlation of the industrial data to make timely predictions in the production process, such as fault prediction and yield prediction.
Autoregressive-Model-Based Methods for Online Time Series Prediction with Missing Values: an Experimental Evaluation
In this paper, we focus on online methods for AR-model-based time series prediction with missing values.
LSTM-based Flow Prediction
In this paper, a method of prediction on continuous time series variables from the production or flow -- an LSTM algorithm based on multivariate tuning -- is proposed.
Automated Detection and Type Classification of Central Venous Catheters in Chest X-Rays
Central venous catheters (CVCs) are commonly used in critical care settings for monitoring body functions and administering medications.
Error Detection in a Large-Scale Lexical Taxonomy
Motived by this, we measure the relation of two concepts by the distance between their corresponding instances and detect errors within the intersection of the conflicting concept sets.
Predicting Learning Status in MOOCs using LSTM
Real-time and open online course resources of MOOCs have attracted a large number of learners in recent years.
Impacts of Dirty Data: and Experimental Evaluation
Data quality issues have attracted widespread attention due to the negative impacts of dirty data on data mining and machine learning results.
Hierarchical Spatial-aware Siamese Network for Thermal Infrared Object Tracking
In this paper, we cast the TIR tracking problem as a similarity verification task, which is coupled well to the objective of the tracking task.
A Hybrid Solution to improve Iteration Efficiency in the Distributed Learning
Currently, many machine learning algorithms contain lots of iterations.
