IJCNN 2020

440 papers
The 2020 International Joint Conference on Neural Networks (IJCNN) featured 546 papers, with research focusing on domain adaptation and the development of invariant representations. Key themes involved improving model generalization through statistical alignment and unsupervised learning. Knowledge distillation was also a major area of study, particularly regarding collaborative training and dynamic weighting for adaptive model training. Additionally, the conference highlighted advancements in model robustness, such as adversarial purification via generative manifold reconstruction and geometric stability for deep neural networks. Other research directions included continual learning through feature stabilization and efficient optimization for dense prediction. Practical applications presented during the event ranged from traffic signal control using centralized coordinators to multimodal autoencoders for music recommendation and transformer-based architectures for abstractive text summarization. Prolific authors contributing to this year's proceedings included Imran Razzak, Albert Bifet, and Saeeda Naz. The research collectively addressed the challenges of making neural networks more adaptive, resilient, and efficient across diverse data environments.

Top Research Directions

Research directions most represented by IJCNN 2020 papers.

Supervised Dimensionality Reduction 3
Clean Accuracy Degradation in Machine Learning Defenses 3
Mask-Aware Convolutions for Incomplete Data 2
Decoupling Representation and Classifier Learning 2
Dimensionality Reduction via Autoencoder Bottlenecks 2
Mixup Regularization via Linear Sample Interpolation 2
Eliminating Spurious Feature Reliance in Medical Imaging Models 2
Global Context Modeling via Non-Local Spatial Attention 2
Bridging the Discrete and Continuous Reinforcement Learning Divide 2
Stacked Generalization for Heterogeneous Ensemble Learning 2
Safe Reinforcement Learning via Constrained Markov Decision Processes 2
Sample Efficient Reinforcement Learning 2
Incremental Model Updates for Continuous Data Streams 2
Learning in Non-Stationary Data Streams 2
Bypassing the Computational Bottleneck of Adversarial Training 2

Top Authors

AuthorPapers
Imran Razzak8
Albert Bifet5
Andreas Dengel5
Cleber Zanchettin5
Muhammad Shafique5
Alberto Marchisio4
Dongbin Zhao4
Guangquan Zhang4
Jie Lu4
Lina Yao4
Qinru Qiu4
Sarah Monazam Erfani4
Tingwen Liu4
A. K. Qin3
Bin Wang3
Christopher Leckie3
David Macêdo3
Dinh Phung3
Fakhri Karray3
Ivan Y Tyukin3

Impactful Papers

Papers from IJCNN 2020 that shaped research clusters.

Foundational

Influential

Papers

Title
Geodesic Clustering of Positive Definite Matrices For Classification of Mental Disorder Using Brain Functional Connectivity
GISNet: Graph-Based Information Sharing Network For Vehicle Trajectory Prediction
GPU-based State Adaptive Random Forest for Evolving Data Streams
Grammatical Error Detection with Self Attention by Pairwise Training
Graph Convolutional Networks for Target-oriented Opinion Words Extraction with Adversarial Training
Hawkes Process Classification through Discriminative Modeling of Text
HDF: Hybrid Deep Features for Scene Image Representation
HeteGraph: A Convolutional Framework for Graph Learning in Recommender Systems
Heterogeneous Graph Attention Networks for Early Detection of Rumors on Twitter
Heterogeneous Information Network Embedding with Convolutional Graph Attention Networks
Hierarchical Deep Reinforcement Learning Approach for Multi-Objective Scheduling With Varying Queue Sizes
Hierarchical-Task Reservoir for Anytime POS Tagging from Continuous Speech
HIME: Mining and Ensembling Heterogeneous Information for Protein-Protein Interactions Prediction
HLNet: Modeling High and Low Frequencies for Scene Parsing
Hybridization of Data and Model based Object Detection for Tracking in Flash Lidars
Hyperparameter Optimization in Binary Communication Networks for Neuromorphic Deployment
Identity-Preserving Realistic Talking Face Generation
I didn't mean what I wrote! Exploring Multimodality for Sarcasm Detection
IEDQN: Information Exchange DQN with a Centralized Coordinator for Traffic Signal Control
Image Co-segmentation with Multi-Scale Dual-Cross Correlation Network
Improved Hierarchical Clustering with Non-locally Enhanced Features for Unsupervised Person Re-identification
Improved Policy Extraction via Online Q-Value Distillation
Improved Stochastic Synapse Reinforcement Learning for Continuous Actions in Sharply Changing Environments
Improving Abstractive Summarization with Iterative Representation
Improving Abstractive Text Summarization with History Aggregation
Improving Discrete Latent Representations With Differentiable Approximation Bridges
Improving Generalization Performance of Adaptive Learning Rate by Switching from Block Diagonal Matrix Preconditioning to SGD
Improving Image Autoencoder Embeddings with Perceptual Loss
Improving k-Means Clustering Performance with Disentangled Internal Representations
Improving Neural Network Learning Through Dual Variable Learning Rates
Improving Self-Adaptation For Multi-Sensor Activity Recognition with Active Learning
Improving Single and Multi-View Blockmodelling by Algebraic Simplification
Improving STDP-based Visual Feature Learning with Whitening
Improving Video Instance Segmentation by Light-weight Temporal Uncertainty Estimates
"I'm Sorry Dave, I'm Afraid I Can't Do That" Deep Q-Learning from Forbidden Actions
Indoor Navigation for Mobile Agents: A Multimodal Vision Fusion Model
Information Enhanced Graph Convolutional Networks for Skeleton-based Action Recognition
Interpretable Time-series Classification on Few-shot Samples
Interpreting Deep Models through the Lens of Data
IO-aware Factorization Machine for User Response Prediction
Is Spiking Secure? A Comparative Study on the Security Vulnerabilities of Spiking and Deep Neural Networks
IT-Block: Inverted Triangle Block embedded U-Net for Medical Image Segmentation
Joint Entity Linking and Relation Extraction with Neural Networks for Knowledge Base Population
Joint Progressive Knowledge Distillation and Unsupervised Domain Adaptation
K-mer Neural Embedding Performance Analysis Using Amino Acid Codons
k-Nearest Neighbor based Clustering with Shape Alternation Adaptivity
Knowledge-based Context-aware Multi-turn Conversational Model with Hierarchical Attention
Knowledge Grounded Pre-Trained Model For Dialogue Response Generation
Knowledge-guided Deep Reinforcement Learning for Interactive Recommendation
KTAN: Knowledge Transfer Adversarial Network

« prev Page 5/9 next »