ICDE 2022

250 papers
The 2022 edition of the International Conference on Data Engineering (ICDE) featured 392 papers, with a focus on the intersection of data management and machine learning. Key research themes included algorithmic fairness, particularly regarding intersectional groups and matroid constrained optimization, as well as scalable model explanation through approximated Shapley values. Federated learning incentives and data valuation for machine learning were also prominent topics. In the domain of graph data, researchers explored automated data augmentation for contrastive learning and adversarial attacks on black-box models. Additional contributions addressed practical data engineering challenges such as cost-effective collaborative annotation systems, language-aware indexing for path queries, and multivariate anomaly detection using self-learning graph convolutional networks. Prolific authors contributing to the program included Xuemin Lin, Wenjie Zhang, and Lei Chen. The research presented reflected a trend toward making machine learning models more interpretable, fair, and efficient within large-scale data systems.

Top Research Directions

Research directions most represented by ICDE 2022 papers.

Generalizing Graph Algorithms to Directed and Weighted Networks 2
Balancing Power Law Workloads in Parallel Graph Processing 2
Overcoming the All Pairs Shortest Path Bottleneck 2
Incremental Maintenance of Dynamic Graph Indices 2
Scaling Graph Processing Beyond Main Memory 2
Generalizing Influence Maximization Across Diffusion Models 1
Socially Aware Team Formation Algorithms 1
Diversity Aware Trajectory Sampling 1
Decomposing the Total Error of Generative Models 1
Representative Benchmarking for Diverse Data Systems 1
Scaling Shapley Values via Stochastic Sampling and Surrogates 1
Scaling Data Systems via Probabilistic Membership Testing 1
Multi-Task Learning for Recommendation Systems 1
Shared Query Execution for Concurrent Workloads 1
Overcoming Augmentation Dependency in Graph Contrastive Learning 1

Top Authors

AuthorPapers
Xuemin Lin17
Wenjie Zhang15
Lei Chen11
Ying Zhang10
Guoren Wang8
Ye Yuan8
Yunjun Gao7
Bin CUI6
Christian S. Jensen6
Lu Qin6
Bin Yang5
Cheng Long5
Jeffrey Xu Yu5
Jianliang Xu5
Xiaoyang Wang5
Chen Chen4
Chenjuan Guo4
Dong Wen4
Hongzhi Yin4
Kai Wang4

Impactful Papers

Papers from ICDE 2022 that shaped research clusters.

Influential

Papers

Title
Fairness-Aware Range Queries for Selecting Unbiased Data
Farming Your ML-based Query Optimizer's Food
Fast Adaptive Similarity Search through Variance-Aware Quantization
Fast Error-Bounded Distance Distribution Computation (Extended Abstract)
Fast Reachability Queries Answering based on RCN Reduction (Extended abstract)
Feature Augmentation with Reinforcement Learning
FedADMM: A Robust Federated Deep Learning Framework with Adaptivity to System Heterogeneity
Federated Learning on Non-IID Data Silos: An Experimental Study
FedKNOW: Federated Continual Learning with Signature Task Knowledge Integration at Edge
Field-aware Variational Autoencoders for Billion-scale User Representation Learning
Finding Critical Users in Social Communities via Graph Convolutions (Extended Abstract)
Finding Top-r Influential Communities under Aggregation Functions
Fluid: Dataset Abstraction and Elastic Acceleration for Cloud-native Deep Learning Training Jobs
Frequency-based Randomization for Guaranteeing Differential Privacy in Spatial Trajectories
Gaia: Graph Neural Network with Temporal Shift aware Attention for Gross Merchandise Value Forecast in E-commerce
GECCO: Constraint-driven Abstraction of Low-level Event Logs
GloDyNE: Global Topology Preserving Dynamic Network Embedding (Extended Abstract)
GPU-accelerated Proximity Graph Approximate Nearest Neighbor Search and Construction
GQP: A Framework for Scalable and Effective Graph Query-based Pricing
GridTuner: Reinvestigate Grid Size Selection for Spatiotemporal Prediction Models
Grow-and-Clip: Informative-yet-Concise Evidence Distillation for Answer Explanation
GX-Plug: a Middleware for Plugging Accelerators to Distributed Graph Processing
HET-KG: Communication-Efficient Knowledge Graph Embedding Training via Hotness-Aware Cache
Hierarchical Core Decomposition in Parallel: From Construction to Subgraph Search
Hierarchical Representation Learning for Attributed Networks
Highly Efficient String Similarity Search and Join over Compressed Indexes
Horae: A Graph Stream Summarization Structure for Efficient Temporal Range Query
How Learning Can Help Complex Cyclic Join Decomposition
Human-Drone Collaborative Spatial Crowdsourcing by Memory-Augmented and Distributed Multi-Agent Deep Reinforcement Learning
HybridGNN: Learning Hybrid Representation for Recommendation in Multiplex Heterogeneous Networks
Hybrid Subgraph Matching Framework Powered by Sketch Tree for Distributed Systems
Identification for Deep Neural Network: Simply Adjusting Few Weights!
IKAROS: An Indoor Keyword-Aware Routing System
imDedup: A Lossless Deduplication Scheme to Eliminate Fine-grained Redundancy among Images
Improving Fairness for Data Valuation in Horizontal Federated Learning
Improving Prediction-Based Lossy Compression Dramatically via Ratio-Quality Modeling
Index-based Structural Clustering on Directed Graphs
Influence-aware Task Assignment in Spatial Crowdsourcing
Intent Mining: A Social and Semantic Enhanced Topic Model for Operation-Friendly Digital Marketing
IPS: Instance Profile for Shapelet Discovery for Time Series Classification
Jarvis: Large-scale Server Monitoring with Adaptive Near-data Processing
Joint Evidential $K$-Nearest Neighbor Classification
Knowledge Enhanced Person-Job Fit for Talent Recruitment
k-Pleased Querying (Extended Abstract)
Language-aware Indexing for Conjunctive Path Queries
LAN: Learning-based Approximate k-Nearest Neighbor Search in Graph Databases
Lasagne: A Multi-Layer Graph Convolutional Network Framework via Node-aware Deep Architecture (Extended Abstract)
Learning Evolvable Time-series Shapelets
Learning Graph Convolutional Networks based on Quantum Vertex Information Propagation (Extended Abstract)
Learning What You Need from What You Did: Product Taxonomy Expansion with User Behaviors Supervision

« prev Page 3/5 next »