ICDE 2024

389 papers
The 2024 IEEE International Conference on Data Engineering (ICDE) featured 583 papers covering a broad range of topics in data management, privacy, and machine learning integration. A primary research direction involved federated learning, specifically addressing model heterogeneity, privacy leakage, and robustness against adversarial model poisoning. Graph neural networks (GNNs) were also prominent, with studies investigating link prediction, community search in heterogeneous networks, and differential privacy applications. Additional research themes included advancements in natural language processing and semantic analysis, such as hybrid semantic similarity for textual alignment and scaling NLP with distant supervision. The conference also covered temporal data analysis, including differentiable temporal alignment and segmented regression for identifying inflection points. Industrial and practical applications were represented by work on data lake storage and functional dependency discovery in outsourced databases. Prolific contributors to this edition included researchers such as Xiaofang Zhou, Xuemin Lin, and Yunjun Gao.

Top Research Directions

Research directions most represented by ICDE 2024 papers.

Mitigating Graph Over-Smoothing via Contrastive Regularization 2
The Point Adjustment Bias in Time Series Anomaly Detection 2
Mapping Optimization Problems to Quadratic Unconstrained Binary Optimization 2
Robust Graph Representation Learning for Complex Topologies 2
Automated Model Selection for Anomaly Detection 2
Predicting Downstream Performance Without Fine Tuning 2
Overcoming the Homophily Assumption in Graph Neural Networks 2
Accelerating Neural Architecture Search Without Full Model Training 2
Attention Based Adaptive Feature Fusion 2
Over-Smoothing in Graph Neural Networks 2
Incremental Maintenance of Dynamic Graph Indices 2
Federated Learning with Diverse Model Architectures 2
Informative Anchor Selection for Scalable Machine Learning 1
Algorithmic Complexity Vulnerabilities in Regular Expression Engines 1
Incremental Execution for Iterative Machine Learning Pipelines 1

Top Authors

AuthorPapers
Xiaofang Zhou23
Guoren Wang16
Lei Chen16
Xuemin Lin14
Yunjun Gao13
Lu Chen12
Kai Zheng11
Ye Yuan11
Bin CUI10
Hongzhi Wang10
Christian S. Jensen9
Wenjie Zhang9
Hongzhi Yin8
Wentao Zhang8
Tong Yang7
Haibo Hu6
Jianliang Xu6
Pengpeng Zhao6
Yan Zhao6
Peng Cheng5

Impactful Papers

Papers from ICDE 2024 that shaped research clusters.

Influential

Papers

Title
Representation Learning of Tangled Key-Value Sequence Data for Early Classification
Resistance Eccentricity in Graphs: Distribution, Computation and Optimization
Resource Allocation with Service Affinity in Large-Scale Cloud Environments
RobFL: Robust Federated Learning via Feature Center Separation and Malicious Center Detection
Robust Auto-Scaling with Probabilistic Workload Forecasting for Cloud Databases
Routing-Guided Learned Product Quantization for Graph-Based Approximate Nearest Neighbor Search
Routing with Massive Trajectory Data
SACH: Significant-Attributed Community Search in Heterogeneous Information Networks
SAGDFN: A Scalable Adaptive Graph Diffusion Forecasting Network for Multivariate Time Series Forecasting
Scalable Community Search with Accuracy Guarantee on Attributed Graphs
Scalable Distance Labeling Maintenance and Construction for Dynamic Small-World Networks
Scalable Overspeed Item Detection in Streams
Scaling Up Multivariate Time Series Pre-Training with Decoupled Spatial-Temporal Representations
Search to Fine-Tune Pre-Trained Graph Neural Networks for Graph-Level Tasks
SecMdp: Towards Privacy-Preserving Multimodal Deep Learning in End-Edge-Cloud
Secure and Practical Functional Dependency Discovery in Outsourced Databases
Secure Normal Form: Mediation Among Cross Cryptographic Leakages in Encrypted Databases
Self-Training GNN-based Community Search in Large Attributed Heterogeneous Information Networks
Semi-Asynchronous Online Federated Crowdsourcing
Separation Is for Better Reunion: Data Lake Storage at Huawei
SES: Bridging the Gap Between Explainability and Prediction of Graph Neural Networks
SeSeMI: Secure Serverless Model Inference on Sensitive Data
SGCL: Semantic-aware Graph Contrastive Learning with Lipschitz Graph Augmentation
SharDAG: Scaling DAG-Based Blockchains Via Adaptive Sharding
Share: Stackelberg-Nash based Data Markets
Short-Text Author Linking Through Multi-Facet Temporal-Textual Embedding (Extended Abstract)
ShrinkHPO: Towards Explainable Parallel Hyperparameter Optimization
S i 1 o F use: Cross-silo Synthetic Data Generation with Latent Tabular Diffusion Models
SoulMate: Short-Text Author Linking Through Multi-Aspect Temporal-Textual Embedding (Extended Abstract)
SparDL: Distributed Deep Learning Training with Efficient Sparse Communication
SPES: Towards Optimizing Performance-Resource Trade-Off for Serverless Functions
SQL++: We Can Finally Relax!
SSDRec: Self-Augmented Sequence Denoising for Sequential Recommendation
ST-ABC: Spatio-Temporal Attention-Based Convolutional Network for Multi-Scale Lane-Level Traffic Prediction
Stable Heterogeneous Treatment Effect Estimation across Out-of-Distribution Populations
STEM: Streaming-Based FPGA Acceleration for Large-Scale Compactions in LSM KV
StructRide: A Framework to Exploit the Structure Information of Shareability Graph in Ridesharing
Structure- and Logic-Aware Heterogeneous Graph Learning for Recommendation
SWISP: Distributed Convoy Mining via Sliding Window-based Indexing and Sub-track Partitioning
Sylvie: 3D-Adaptive and Universal System for Large-Scale Graph Neural Network Training
Synergies Between Graph Data Management and Machine Learning in Graph Data Pipeline
Target-agnostic Source-free Domain Adaptation for Regression Tasks
Task-Oriented GNNs Training on Large Knowledge Graphs for Accurate and Efficient Modeling
Task Recommendation in Spatial Crowdsourcing: A Trade-Off Between Diversity and Coverage
TASKS: A Real-Time Query System for Instant Error-Tolerant Spatial Keyword Queries on Road Networks
TELL: Efficient Transaction Execution Protocol Towards Leaderless Consensus
Temporal-Frequency Masked Autoencoders for Time Series Anomaly Detection
Temporal Graph Generation Featuring Time-Bound Communities
Time-Constrained Continuous Subgraph Matching Using Temporal Information for Filtering and Backtracking
TimeDRL: Disentangled Representation Learning for Multivariate Time-Series

« prev Page 7/8 next »