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

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.

Defend from Scratch: A Diffusion-based Proactive Defense Method for Unauthorized Speech Synthesis.- Transformers As Approximations of Solomonoff Induction.- Interpreting Decision Transformer: Insights from Continuous Control Tasks.- Flexible-order Feature-interaction for Mixed Continuous and Discrete Variables with Group-level Interpretability.- Critical Feature Sifting and Dynamic Aggregation for Anomalous Audio Sequence Detection.- Parallel Interpretation Network via Semantic Visual Probe and Counterfactual Verification.- Real-Time Decentralized M2M Decision-Making via Deep Learning and Incremental Learning.- Explainable Federated Stacking Models with Encrypted Gradients for Secure Kidney Medical Imaging Diagnosis.- DDFGNN: Dual-dimensionality Fusion Graph Neural Network for Social Bot Detection.- A Motif-based Graph Convolution Network for Stock Trend Prediction.- VAGNN: Advancing the Generalization of Graph Neural Networks.- TrajAngleNet: Transformer-based Trajectory Prediction through Multi-Task Learning with Angle Prediction.- Correlation Disentangling and Spatio-Temporal Cooperative Optimizing Network for Temperature Prediction Revision.- Hierarchical Adaptive Position Encoding-based Transformer for Point Cloud Analysis.- In-context Learning for Temperature Field Reconstruction under Multiple Layouts.- Loosely coupled oscillators as a correlate of behavioral control circuits within the central complex of the fruit fly.- EL-LSTM: A Multivariate Time Series Forecasting Model Combining Spiking Neurons and Long Short-Term Memory Networks.- A Two-Stage Network for Enhanced Intracranial Artery 3D Segmentation in TOF-MRA Volume.- Independence Constrained Disentangled Representation Learning from pistemological Perspective.- Utilizing Small and Large Spectral Radii for Appropriate Reservoir Computing Design.- Noisy Deep Ensemble: Accelerating Deep Ensemble Learning via Noise Injection.- LCNet: Lightning Hierarchical Convolution for Occupancy Flow Prediction.- FedTS: Leveraging Teacher-Student Architecture in Federated Learning against Model Heterogeneity in Edge Computing Scenarios.- Physics-informed antisymmetric recurrent neural networks for solving nonlinear partial differential equations.- APS: An Adaptive Policy Switching Framework to Improve the Generalization of Branching.- Efficient Pruning and Compression Techniques for Convolutional Neural Networks to Preserve Knowledge and Optimize Performance.- Enhancing Convnets with Pruning and Symmetry-Based Filter Augmentation.- Improved Approximation Algorithms for the Cumulative Vehicle Routing Problem.