Graph Mining
Co-Authorship Prediction Based on Temporal Graph Attention
Degree-specific Topology Learning for Graph Convolutional Network
Simplifying Graph Convolutional Networks as Matrix Factorization
RASP: Graph Alignment through Spectral Signatures
FANE: A Fusion-based Attributed Network Embedding Framework
Data Mining
What Have We Learned from Open Review?
Unsafe Driving Behavior Prediction for Electric Vehicles
Resource Trading with Hierarchical Game for Computing-Power Network Market
Analyze and Evaluate Database-Backed Web Applications with WTool
Semi-supervised Variational Multi-view Anomaly Detection
A Graph Attention Network Model for GMV Forecast on Online Shopping Festival
Suicide Ideation Detection on Social Media during COVID-19 via Adversarial and Multi-task Learning
Data Management
An Efficient Bucket Logging for Persistent Memory
Data Poisoning Attacks on Crowdsourcing Learning
Dynamic Environment Simulation for Database Performance Evaluation
LinKV: an RDMA-enabled KVS for High Performance and Strict Consistency under Skew
Cheetah: An Adaptive User-space Cache for Non-volatile Main Memory File Systems
Topic Model and Language Model Learning
Chinese Word Embedding Learning with Limited Data
Sparse Biterm Topic Model for Short Texts
EMBERT: A Pre-trained Language Model for Chinese Medical Text Mining
Self-Supervised Learning for Semantic Sentence Matching with Dense Transformer Inference Network
An Explainable Evaluation of Unsupervised Transfer Learning for Parallel Sentences Mining
Text Analysis
Leveraging Syntactic Dependency and Lexical Similarity for Neural Relation Extraction
A Novel Capsule Aggregation Framework for Natural Language Inference
Learning Modality-Invariant Features by Cross-Modality Adversarial Network for Visual Question Answering
Difficulty-controllable Visual Question Generation
Incorporating Typological Features into Language Selection for Multilingual Neural Machine Translation
Removing Input Confounder for Translation Quality Estimation via a Causal Motivated Method
Text Classification
Learning Refined Features for Open-World Text Classification
Emotion Classification of Text Based on BERT and Broad Learning System
Improving Document-level Sentiment Classification with User-Product Gated Network
Integrating RoBERTa Fine-Tuning and User Writing Styles for Authorship Attribution of Short Texts
Dependency Graph Convolution and POS Tagging Transferring for Aspect-based Sentiment Classification
Machine Learning
DTWSSE: Data Augmentation with a Siamese Encoder for Time Series
PT-LSTM: Extending LSTM for Efficient processing Time Attributes in Time Series Prediction
Loss Attenuation for Time Series Prediction Respecting Categories of Values
PFL-MoE: Personalized Federated Learning Based on Mixture of Experts
A New Density Clustering Method using Mutual Nearest Neighbor.-