Neural Information Processing 31st International Conference, ICONIP 2024, Auckland, New Zealand, December 2–6, 2024, Proceedings, Part VI

The eleven-volume set LNCS 15286-15296 constitutes the refereed proceedings of the 31st International Conference on Neural Information Processing, ICONIP 2024, held in Auckland, New Zealand, in December 2024.
The 318 regular papers presented in the proceedings set were carefully reviewed and selected from 1301 submissions. They focus on four main areas, namely: theory and algorithms; cognitive neurosciences; human-centered computing; and applications.

Ranking Region-based OD-Betweenness Centrality in Road Networks.- Mining Fuzzy Partial Periodic Frequent Patterns in Very Large Temporal Databases.- Style Miner: Find Significant and Stable Factors in Time Series with Constrained Reinforcement Learning.- Ensemble Learning Prediction Based on Comprehensive Factors for Portfolio Optimization.- TDAT: A Real-time Two-stage DDoS Attacks Detector Based on Anomaly Transformer.- Unified Mask Graph Modeling for Incomplete Tabular Learning.- Learning Granularity Representation for Temporal Knowledge Graph  Completion.- MPLinear: Multiscale Patch Linear Model for Long-Term Time Series Forecasting.- Residual Broad Learning System with Variational Autoencoder for Robust Regression.- STEncoder: Robust Decomposition for Time Series Forecasting.- Fine-Grained Common Knowledge Learning for Domain Adaptive Few-shot Relation Extraction.- DMGCL: Denoising Multi-View Graph Contrastive Learning for Robust Recommendation.- STMGFN: Spatio-Temporal Multi-Graph Fusion Network for Traffic Flow Prediction.- Refined Sentiment Analysis Using POS Features and LDA: Mitigating Polysemy and Sparsity with BERT Contextual Embedding.- Table-Based Two-Stage Relation Classification Method for Trigger-Free Document-Level Event Extraction.- CDIG: Customizable Dual Interaction Graph module for News Recommendation.- VEBiLSTM: A Neural Network for Field-road Classification using Enhanced Spatiotemporal Features.- Seq-LSTM-Conv: Multi-sequence Aggregated Forecasting Using LSTM and Convolutional Neural Networks.- Test-time Adaptation with Angular Distance-based Prediction.- FedAKD:Heterogeneous Graph Federated Learning Framework based on Data Augmentation and Knowledge Distillation.- TSIV: A Two-Stage Approach for Identifying Encrypted Video Traffic in Unstable Network.- Who is the Writer?Identifying the Generative Model by Writing Style.- RAEDiff: Diffusion Models Enable Self-Generation and Self-Recovery of Reversible Adversarial Examples.- OKey: Towards More Controllable, Secure and Robust Diffusion Model Image Steganography Using Optimized Key.- Automated Mining of Multi-Dimensional Information from APT Malware for Effective Feature Analysis and Threat Actor Attribution.- PaPa: Propagation Pattern Enhanced Prompt Learning for Zero-shot Rumor Detection.