IJCNN

5,415 papers1,455 directions
The International Joint Conference on Neural Networks (IJCNN) is a long-standing research venue in the fields of machine learning and artificial intelligence, with a publication history spanning from 1990 to 2025. With over 6,500 papers in its corpus, the conference serves as a platform for the dissemination of work related to neural computation and its applications. It features contributions from researchers such as Jianzong Wang, Jing Xiao, Stefan Wermter, and Irwin King, among others. The venue is characterized by a strong emphasis on neural network architectures and optimization techniques. Key research directions include the development of energy-efficient spiking neural networks for resource-constrained hardware, spike-driven computation, and constant memory training for recurrent networks. Additionally, the conference publishes work on managing concept drift in real-time data streams, interpretable machine learning, and generative replay strategies for data-free continual learning. Recent publications at IJCNN reflect a broad range of contemporary AI applications, including multi-modal knowledge graph generation, personalized recommendation systems using large language models, and physics-compliant text-to-3D shape generation. The venue also covers specialized topics such as temporal-spatial data augmentation for point clouds, 360° image captioning, and AI frameworks for ESG performance prediction. This breadth of topics positions the conference as a venue for both fundamental neural network research and applied machine learning across various data modalities.

Papers by Year

2025 595
2024 667
2023 438
2022 493
2021 564
2020 440
2019 353
2018 232
2017 216
2016 247
2015 144
2014 180
2013 95
2012 124
2011 65
2010 75
2009 56
2008 95
2007 67
2006 97
2005 54
2004 61
2003 51
1999 76
1990 20

Top Research Directions

Research directions most represented by papers from this venue.

Accelerating Neural Architecture Search Without Full Model Training 11
Knowledge Retention in Continual Deep Learning 11
Clean Accuracy Degradation in Machine Learning Defenses 11
Bypassing the Computational Bottleneck of Adversarial Training 8
Compressing Large Foundation Models via Knowledge Distillation 7
Generalizing Deep Learning Methods Beyond Image Classification 7
Self-Explainable Neural Networks without Performance Loss 7
Learning in Non-Stationary Data Streams 7
Compressing Deep Learning Representations with PCA 6
Supervised Dimensionality Reduction 5
Generalizing Model Pruning Across Diverse Neural Architectures 5
Adversarial Training for Robust Machine Learning 5
Modeling Temporal Dependencies with Recurrent Neural Networks 5
Understanding Gradient Masking in Adversarial Defenses 5
Cross Model Adversarial Transferability 5

Top Authors

AuthorPapers
Stefan Wermter53
Jianzong Wang48
Jing Xiao38
Junbin Gao36
Dongbin Zhao34
Muhammad Shafique33
Cleber Zanchettin32
Irwin King31
Badong Chen29
Barbara Hammer27
Cesare Alippi27
Michael Blumenstein27
Manuel Roveri25
Nanning Zheng24
Jie Lu22
Cuntai Guan21
Guangquan Zhang20
Saibal Mukhopadhyay20
Daniel Dajun Zeng19
Furao Shen19

Impactful Papers

Papers from this venue that shaped research clusters.

Foundational

Influential

Related Venues

Venues with the most similar research cluster distributions.

Papers

TitleYear
Stochastic Intervention for Causal Effect Estimation2021
Stock Movement Prediction on Ex-Dividend Day Using Event Specific Features and Machine Learning Techniques2021
S-TRIGGER: Continual State Representation Learning via Self-Triggered Generative Replay2021
Structure and Randomness in Planning and Reinforcement Learning2021
STSIR: A Spatial Temporal Pandemic Model with Mobility Data - A COVID-19 Study2021
Summary2vec: Learning Semantic Representation of Summaries for Healthcare Analytics2021
Systematic Generalization in Neural Networks-based Multivariate Time Series Forecasting Models2021
Systolic-Array Spiking Neural Accelerators with Dynamic Heterogeneous Voltage Regulation2021
TA-GAN: GAN based Traffic Augmentation for Imbalanced Network Traffic Classification2021
Target-aware for Few-shot Segmentation2021
Targeted Attacks in Hierarchical Settings via Convex Programming2021
Temporal Convolutional Attention Neural Networks for Time Series Forecasting2021
Temporal Dependent Local Learning for Deep Spiking Neural Networks2021
Temporal Pattern Coding in Deep Spiking Neural Networks2021
Tensorial Time Series Prediction via Tensor Neural Ordinary Differential Equations2021
Tensor-Train Recurrent Neural Networks for Interpretable Multi-Way Financial Forecasting2021
Text Generation with Syntax - Enhanced Variational Autoencoder2021
The Hammer and the Nut: Is Bilevel Optimization Really Needed to Poison Linear Classifiers?2021
Think About Boundary: Fusing Multi-level Boundary Information for Landmark Heatmap Regression2021
Time-Aware Representation Learning of Knowledge Graphs2021
Topic Enhanced Multi-head Co-Attention: Generating Distractors for Reading Comprehension2021
Topological Gradient-based Competitive Learning2021
Toward Application of Continuous Power Forecasts in a Regional Flexibility Market2021
Towards Consistent Predictive Confidence through Fitted Ensembles2021
Towards Feature-free TSP Solver Selection: A Deep Learning Approach2021
Towards Interpretable and Reliable Reading Comprehension: A Pipeline Model with Unanswerability Prediction2021
Towards Predictive Analytics in Mental Health Care2021
Towards Silhouette-Aware Human Detection in Depth Images2021
Towards Unbiased Random Features with Lower Variance For Stationary Indefinite Kernels2021
Training Classifiers that are Universally Robust to All Label Noise Levels2021
Training Energy-Efficient Deep Spiking Neural Networks with Single-Spike Hybrid Input Encoding2021
TRANSFAKE: Multi-task Transformer for Multimodal Enhanced Fake News Detection2021
Transfer Ability of Monolingual Wav2vec2.0 for Low-resource Speech Recognition2021
Transfer Learning Application for Berries Yield Forecasting using Deep Learning2021
Transformer-based Relation Detect Model for Aspect-based Sentiment Analysis2021
TransVae: A Novel Variational Sequence-to-Sequence Framework for Semi-supervised Learning and Diversity Improvement2021
Triplet Angular Loss for Pose-Robust Face Recognition2021
Trust, but Verify: Alleviating Pessimistic Errors in Model-Based Exploration2021
TSA-GAN: A Robust Generative Adversarial Networks for Time Series Augmentation2021
Two-Dimensional Learning Rate Decay: Towards Accurate Federated Learning with Non-IID Data2021
Two-stage Local Spatio-temporal Event Filter based on Adaptive Thresholds2021
Two-Stage Resampling for Convolutional Neural Network Training in the Imbalanced Colorectal Cancer Image Classification2021
TW-TGNN: Two Windows Graph-Based Model for Text Classification2021
UCBVis: Understanding Customer Behavior Sequences with Visual Interactive System2021
UMDSF: Unified Model With Dynamic-Static Features for Personalized Recommendation2021
UMVD-FSL: Unseen Malware Variants Detection Using Few-Shot Learning2021
Uncertainty-Aware Boosted Ensembling in Multi-Modal Settings2021
Undersampling with Support Vectors for Multi-Class Imbalanced Data Classification2021
Understanding Neural Responses to Face Verification of Cross-Domain Representations2021
Unified Batch All Triplet Loss for Visible-Infrared Person Re-identification2021

« prev Page 54/109 next »