IEEE BigData 2021

188 papers
The 2021 IEEE International Conference on Big Data (IEEE BigData 2021) featured 235 papers focusing on data efficiency, large-scale simulation, and advanced machine learning architectures. A central theme was the optimization of data annotation processes, with research addressing the human verification bottleneck, selective sampling for label-efficient learning, and the identification of diminishing returns in data labeling. Other studies explored methods to mitigate recency bias in continual learning and techniques for combating noisy labels in deep learning models. The conference also highlighted applications of big data in societal modeling and public health. This included the development of high-fidelity synthetic populations and the modeling of spatial heterogeneity in infectious disease transmission to inform public health interventions. Technical contributions spanned graph convolutional networks for heterogeneous graphs, privacy-preserving inference, and anomaly detection for high-dimensional sparse data. Prolific contributors to the 2021 edition included researchers such as Da Yan, Philip S. Yu, and Elke A. Rundensteiner.

Top Research Directions

Research directions most represented by IEEE BigData 2021 papers.

Synthetic Anomalies and Distillation for Robust Anomaly Detection 2
The Reproducibility Crisis of Private and Proprietary Datasets 2
Spatial Layout and the Distortion of User Attention 1
Graph Anomaly Detection via Structural Attribute Inconsistency 1
Behavioral Model Mismatch in Learning to Rank 1
Unsupervised Discovery of Latent Behavioral Personas 1
Feature Engineering over Model Complexity 1
Continuous Graph Limits for Transferable Neural Networks 1
Optimizing the Geometric Mean for Imbalanced Learning 1
Reclaiming Latent Information from Noisy Training Data 1
Multi Metric Fusion for Robust Anomaly Detection 1
One-Shot Perturbation for Non-Interactive Differential Privacy 1
Robust Anomaly Detection through Model Ensembles 1
Synthetic Population Generation for Agent Simulations 1
Temporal Sensitivity of Epidemic Intervention Strategies 1

Top Authors

AuthorPapers
Da Yan5
Emmanuel Agu5
Philip S. Yu5
Diego Klabjan4
Elke Rundensteiner4
Kyumin Lee3
Shuhan Yuan3
Yugyung Lee3
Abdulaziz Alajaji2
Andrea L. Bertozzi2
Andrew Lan2
Arun Iyengar2
Chang-Tien Lu2
Depeng Xu2
Dhaval C Patel2
Dong Wang2
Duen Horng Chau2
Evangelos E. Papalexakis2
Feng Xia2
George Karypis2

Impactful Papers

Papers from IEEE BigData 2021 that shaped research clusters.

Foundational

Influential

Papers

Title
Influence of Land Use information over performance when predicting spatiotemporal electricity load demand
Interest-aware Item Combination Prediction
Interpretable Explanations for Probabilistic Inference in Markov Logic
InterpretableSAD: Interpretable Anomaly Detection in Sequential Log Data
Kalman Filtering for Learning with Evolving Data Streams
Keyword-based Topic Modeling and Keyword Selection
Knowledge Graph Representation via Hierarchical Hyperbolic Neural Graph Embedding
Learning Code Representations Using Multifractal-based Graph Networks
Learning Interpretation with Explainable Knowledge Distillation
Logit-based Uncertainty Measure in Classification
Matrix Profile Index Approximation for Streaming Time Series
MedTextSeg: A Deep Dual Sequential Model for Section Segmentation in Medical Reports
MetaHate: A Meta-Model for Hate Speech Detection
MFSL-Net: A Modality Fusion and Shape Learning based Cascaded Network for Prostate Tumor Segmentation
Mitigating Divergence of Latent Factors via Dual Ascent for Low Latency Event Prediction Models
MixNN: Combating Noisy Labels in Deep Learning by Mixing with Nearest Neighbors
MM-trafficEvent: An Interactive Incident Retrieval System for First-view Travel-log Data
Mobility-based Individual POI Recommendation to Control the COVID-19 Spread
Model-Centric and Data-Centric Aspects of Active Learning for Deep Neural Networks
Model Selection in Local Approximation Gaussian Processes: A Markov Random Fields Approach
Mufin: Enriching Semantic Understanding of Sentence Embedding using Dual Tune Framework
Multimodal Product Matching and Category Mapping: Text+Image based Deep Neural Network
Multi-Objective Submodular Optimization with Approximate Oracles and Influence Maximization
Multi-Source Domain Adaptation with Weak Supervision for Early Fake News Detection
Multi-Task and Multi-Scene Unified Ranking Model for Online Advertising
Multi-Temporal Abstraction with Time-Aware Deep Q-Learning for Septic Shock Prevention
MURAL: An Unsupervised Random Forest-Based Embedding for Electronic Health Record Data
Network-based link prediction of scientific concepts - a Science4Cast competition entry
Node-Polysemy Aware Recommendation by Matrix Completion with Side Information
NodeSense2Vec: Spatiotemporal Context-Aware Network Embedding for Heterogeneous Urban Mobility Data
Non-Parallel Text Style Transfer using Self-Attentional Discriminator as Supervisor
On Exploring Attention-based Explanation for Transformer Models in Text Classification
On the combined effect of class imbalance and concept complexity in deep learning
Optimal Branch Location for Cost-effective Inference on Branchynet
Optimizing Bike-Share Repositioning: Networked Inventory Management with Spatiotemporal Modeling
Optimizing Iterative Algorithms for Social Network Sharding
Overcoming Rare-Language Discrimination in Multi-Lingual Sentiment Analysis
Parallel Decoders Guided Lexically Constrained Response Generation
Passive Smartphone Contact Tracing and Continuous COVID-19 Infection Risk Assessment
Personalized Fashion Recommendation from Personal Social Media Data: An Item-to-Set Metric Learning Approach
Placement of DNN Models on Mobile Edge Devices for Effective Video Analysis
Position-based Hash Embeddings For Scaling Graph Neural Networks
Predicting Mental Health Problems with Personality, Behavior, and Social Networks
Pre-training Recommender Systems via Reinforced Attentive Multi-relational Graph Neural Network
Privacy-Preserving Big Data Exchange: Models, Issues, Future Research Directions
Production Machine Learning Frameworks for Geospatial Big Data
Programmatic Database Language Generation for Big Data Applications
Random Sample Partition-Based Clustering Ensemble Algorithm for Big Data
Realistic Transport Simulation for Studying the Impacts of Shared Micromobility Services
Reducing and Exploiting Data Augmentation Noise through Meta Reweighting Contrastive Learning for Text Classification

« prev Page 3/4 next »