ICDE 2023

290 papers
The 2023 edition of ICDE featured 433 papers, with research themes centered on time series analysis, pattern mining, and the reliability of machine learning models. Key areas of investigation included deep seasonal trend decomposition, spatio-temporal forecasting, and efficient pattern mining in temporal graphs. A notable trend was the focus on uncertainty quantification and calibration for deep networks, alongside methods for resolving parameter interference in heterogeneous federated learning. Specific contributions included "Sudowoodo," a framework for contrastive self-supervised learning in data integration, and "Saguaro," an edge computing-enabled hierarchical permissioned blockchain. Research also addressed data stream processing, entity graph learning for user targeting, and functional dependency approximation. Prolific authors for this year included Xuemin Lin, Wenjie Zhang, Xiaofang Zhou, and Ye Yuan. The proceedings reflected an ongoing integration of exogenous context into forecasting models and advancements in high-utility pattern mining beyond traditional downward closure constraints.

Top Research Directions

Research directions most represented by ICDE 2023 papers.

Dynamic Preference Modeling in Interactive Systems 3
Learning on Graphs with Scarce Labels 2
Self Supervised Regularization for Sparse Recommender Systems 2
The Critical Role of Systematic Hyperparameter Optimization 2
Continuous Model Adaptation for Evolving Data Streams 2
Learning in Non-Stationary Data Streams 2
Predictive Transaction Scheduling 1
Estimating the Bayes Error Rate from Data 1
Preserving Local Structure in Evolving Embeddings 1
Mapping Irregular Graphs to Regular Grid Representations 1
Axiomatic Characterization of Committee Scoring Rules 1
The Economics of Non-Rivalrous Data Markets 1
Scaling Decision Models Beyond Binary Choices 1
Personalized Mapping Functions for Cross-Domain Recommendation 1
Decoupling Generation and Selection in Sequence Models 1

Top Authors

AuthorPapers
Xuemin Lin14
Guoren Wang11
Wenjie Zhang10
Xiaofang Zhou7
Ye Yuan7
Bin CUI6
Tong Yang6
Ying Zhang6
Yunjun Gao6
Chi Harold Liu5
Jun Zhou5
JUN ZHOU5
Lu Qin5
Bingsheng He4
Christian S. Jensen4
Ge Yu4
Huaiyu Wan4
Hui Xiong4
Kai Zheng4
Lu Chen4

Impactful Papers

Papers from ICDE 2023 that shaped research clusters.

Influential

Papers

Title
Spatiotemporal Activity Modeling via Hierarchical Cross-Modal Embedding : Extended Abstract
Stable Tuple Embeddings for Dynamic Databases
StreamMLOps: Operationalizing Online Learning for Big Data Streaming & Real-Time Applications
Sudowoodo: Contrastive Self-supervised Learning for Multi-purpose Data Integration and Preparation
TDB: Breaking All Hop-Constrained Cycles in Billion-Scale Directed Graphs
Tele-Knowledge Pre-training for Fault Analysis
The Metaverse Data Deluge: What Can We Do About It?
The Node-Similarity Distribution of Complex Networks and Its Applications in Link Prediction (Extended Abstract)
Time-Aware Location Prediction by Convolutional Area-of-Interest Modeling and Memory-Augmented Attentive LSTM (Extended abstract)
Toward a Unified Framework for Unsupervised Complex Tabular Reasoning
Toward Efficient Automated Feature Engineering
Towards Capacity-Aware Broker Matching: From Recommendation to Assignment
Towards Efficient MIT query in Trajectory Data
Towards Efficient Shortest Path Counting on Billion-Scale Graphs
Towards Explainable Table Interpretation Using Multi-view Explanations
Towards Higher-order Topological Consistency for Unsupervised Network Alignment
Towards Long-Term Time-Series Forecasting: Feature, Pattern, and Distribution
Towards Optimizing Storage Costs on the Cloud
Towards Understanding the Instability of Network Embedding (Extended Abstract)
T-PAIR: Temporal Node pair Embedding for Automatic Biomedical Hypothesis Generation (Extended abstract)
Transferable Feature Selection for Unsupervised Domain Adaptation : Extended Abstract
TSC-AutoML: Meta-learning for Automatic Time Series Classification Algorithm Selection
TxAllo: Dynamic Transaction Allocation in Sharded Blockchain Systems
UADB: Unsupervised Anomaly Detection Booster
Uncertainty Quantification for Traffic Forecasting: A Unified Approach
Understanding the Price of Data in Commercial Data Marketplaces
UniMatch: A Unified User-Item Matching Framework for the Multi-purpose Merchant Marketing
Unshackling Database Benchmarking from Synthetic Workloads
Unsupervised Feature Learning Architecture with Multi-clustering Integration RBM
Unsupervised Graph Outlier Detection: Problem Revisit, New Insight, and Superior Method
Urban Region Representation Learning with Attentive Fusion
VC-dimension and Rademacher Averages of Subgraphs, with Applications to Graph Mining
VEND: Vertex Encoding for Edge Nonexistence Determination
Ver: View Discovery in the Wild
Video Super-Resolution Reconstruction Based on Deep Learning and Spatio-Temporal Feature Self-similarity (Extended abstract)
Visualization Recommendation Through Visual Relation Learning and Visual Preference Learning
Voting-based Opinion Maximization
When Spatio-Temporal Meet Wavelets: Disentangled Traffic Forecasting via Efficient Spectral Graph Attention Networks
Who Would be Interested in Services? An Entity Graph Learning System for User Targeting
Wind-Bell Index: Towards Ultra-Fast Edge Query for Graph Databases

« prev Page 6/6