IEEE BigData 2019

224 papers
The 2019 IEEE International Conference on Big Data (IEEE BigData 2019) featured 295 papers covering diverse domains in data science and computational intelligence. A primary research focus involved geospatial AI and spatiotemporal feature learning, with studies addressing geographic generalization gaps and learning from spatially misaligned labels. Another prominent trend was the optimization of neural networks for hardware, including hardware-aware neural architecture search, energy-efficient event-driven computation, and hardware-software co-optimization. The proceedings also emphasized advancements in representation learning and network analysis. Key contributions included work on semantically enhanced node sequence embeddings (SENSE), non-local attention learning for heterogeneous information networks, and methods for mining networked coevolving time series. Research into data streams remained a core theme, focusing on fast anomaly detection and dynamic ensembles for time-series forecasting. Prolific authors contributing to this year's edition included Philip S. Yu, Elke A. Rundensteiner, and Hanghang Tong. Collectively, the research highlighted a move toward integrating structural awareness and hardware efficiency into large-scale data processing frameworks.

Top Research Directions

Research directions most represented by IEEE BigData 2019 papers.

Adaptive Thresholding for Dynamic Anomaly Detection 2
Overcoming the Geographic Generalization Gap in Remote Sensing 2
Moving Beyond Manual Hyperparameter Tuning 2
Continuous Model Adaptation for Evolving Data Streams 2
Generalizing Influence Maximization Across Diffusion Models 1
Simplex and Polytope Constrained Latent Spaces 1
Measuring Network Polarization with Random Walks 1
Automated Fault Injection for System Resilience 1
Learning Invariant Representations from Multi-Temporal Imagery 1
Pattern Mining Under Non-Monotonic Constraints 1
Relational Graph Modeling for Coordinated Fraud Detection 1
Modeling Exogenous Influence in Social and Information Networks 1
Cross-Framework Interoperability in Deep Learning 1
Distance Dependent Signal Decay in Acoustic Sensing 1
Learnable Activation Functions for Plastic Neural Networks 1

Top Authors

AuthorPapers
Philip S. Yu13
Elke Rundensteiner5
Albert Bifet4
Hanghang Tong4
Yugyung Lee4
Da Yan3
Huiyuan Chen3
Jerry Chun-Wei Lin3
Jiawei Zhang3
Jing Li3
Jun Zhou3
JUN ZHOU3
Ling Liu3
Li Sun3
Qinghua Zheng3
Rongzhe Wei3
Sen Su3
Xiangnan Kong3
Zhongbao Zhang3
Alessandra Russo2

Impactful Papers

Papers from IEEE BigData 2019 that shaped research clusters.

Foundational

Influential

Papers

Title
The Link Regression Problem in Graph Streams
Tile & Merge: Distributed Delaunay Triangulations for Cloud Computing
Towards a Neural-Symbolic Generative Policy Model
Towards Real Time Team Optimization
Training-free Monocular 3D Event Detection System for Traffic Surveillance
TransLand: An Adversarial Transfer Learning Approach for Migratable Urban Land Usage Classification using Remote Sensing
Trust Inference for Rideshare through Co-training on Social Media Data
TsOutlier: Explaining Outliers with Uniform Profiles over IoT Data
Two Problems in Knowledge Graph Embedding: Non-Exclusive Relation Categories and Zero Gradients
Uncertainty-Aware Opinion Inference Under Adversarial Attacks
Understanding Multilingual Communities through Analysis of Code-switching Behaviors in Social Media Discussions
Understanding Spatio-Temporal Urban Processes
Unsupervised Author Disambiguation using Heterogeneous Graph Convolutional Network Embedding
Unsupervised Conditional Adversarial Networks for Tax Evasion Detection
USTAR: Online Multimodal Embedding for Modeling User-Guided Spatiotemporal Activity
Utility-Driven Mining of High Utility Episodes
Visual Anomaly Detection in Event Sequence Data
VulnerCheck: A Content-Agnostic Detector for Online Hatred-Vulnerable Videos
Walk2Privacy: Limiting target link privacy disclosure against the adversarial link prediction
Weakly Supervised Deep Learning Approach in Streaming Environments
Weighted Focus-Attention Deep Network for Fine-grained Image Classification
Wikipedia Polarization and Its Effects on Navigation Paths
Wind Turbine operational state prediction: towards featureless, end-to-end predictive maintenance
Would a File by Any Other Name Seem as Malicious?

« prev Page 5/5