Neural Information Processing: 30th International Conference, ICONIP 2023, Changsha, China, November 20–23, 2023, Proceedings, Part II(14448 Lecture Notes in Computer Science)

The six-volume set LNCS 14447 until 14452 constitutes the refereed proceedings of the 30th International Conference on Neural Information Processing, ICONIP 2023, held in Changsha, China, in November 2023.  The 652 papers presented in the proceedings set were carefully reviewed and selected from 1274 submissions. They focus on theory and algorithms, cognitive neurosciences; human centred computing; applications in neuroscience, neural networks, deep learning, and related fields. 

Table of Contents:
Theory and Algorithms.- Distributed Nash Equilibrium Seeking of Noncooperative Games with Communication Constraints and Matrix Weights.- Accelerated Genetic Algorithm with Population Control for Energy-Aware Virtual Machine Placement in Data Centers.- A Framework of Large-Scale Peer-to-Peer Learning System.- Optimizing 3D UAV Path Planning: An Approach Incorporating Multiple Mechanisms and Beluga Whale Optimizer.- Interactive Attention-Based Graph Transformer for Multi-Intersection Traffic Signal Control.- PatchFinger: A Model Fingerprinting Scheme based on Adversarial Patch.- Attribution of Adversarial Attacks via Multi-Task Learning.- A Reinforcement Learning Method for Generating Class Integration Test Orders Considering Dynamic Couplings.- A Novel Machine Learning Model using CNN-LSTM Parallel Networks for Predicting Ship Fuel Consumption.- Two-Stage Attention Model to Solve Large-Scale Traveling Salesman Problems.- Learning Primitive-aware Discriminative Representations for Few-shot Learning.- Time-Series Forecasting through Contrastive Learning with a Two-Dimensional Self-Attention Mechanism.- Task Scheduling with Multi-strategy Improved Sparrow Search Algorithm in Cloud Datacenters.- Enhanced State-Aware Traffic Light Optimization Control Method.- Impulsive Accelerated Reinforcement Learning for H∞ Control.- MRRC: Multi-Agent Reinforcement Learning with Rectification Capability in Cooperative Tasks.- Latent Causal Dynamics Model for Model-based Reinforcement Learning.- Gradient Coupled Flow: Performance Boosting on Network Pruning by Utilizing Implicit Loss Decrease.- Motif-SocialRec: A Multi-channel Interactive Semantic Extraction Model for Social Recommendation.- Dual Channel Graph Neural Network Enhanced by External Affective Knowledge for Aspect Level Sentiment Analysis.- New predefined-time stability theorem and applications to the fuzzy stochastic memristive neural networks with impulsive effects.- Removing Double Descent with Data-dependent Regularization under Non-Asymptotic View.- FE-YOLOv5:Improved YOLOv5 Network for Multi-scale Drone-captured Scene Detection.- An Improved NSGA-II for UAV Path Planning.- Reimagining China-US Relations Prediction: A Multi-Modal, Knowledge-Driven Approach with KDSCINet.- A Graph Convolution Neural Network for User-group Aided Personalized Session-based Recommendation.- Disentangling Node Metric Factors For Temporal Link Prediction.- Action Prediction for Cooperative Exploration in Multi-agent Reinforcement Learning.- SLAM: A Lightweight Spatial Location Attention Module for Object Detection.- A Novel Interaction Convolutional Network Based on Dependency Trees for Aspect-level Sentiment Analysis.- Efficient Collaboration via Interaction Information in Multi-Agent System.- A Deep Graph Matching-Based Method for Trajectory Association in Vessel Traffic Surveillance.- Few-shot Anomaly Detection in Text with Deviation Learning.- MOC: Multi-modal Sentiment Analysis via Optimal Transport and Contrastive Interactions.- Two-Phase Semantic Retrieval For Explainable Multi-Hop Question Answering.- Efficient Spiking Neural Architecture Search with Mixed Neuron Models and Variable Thresholds.- Towards Scalable Feature Selection: An Evolutionary Multitask Algorithm Assisted by Transfer Learning Based Co-surrogate.- CAS-NN: a robust cascade neural network without compromising clean accuracy.- Multi-Scale Information Fusion Combined with Residual Attention for Text Detection.- Encrypted-SNN: A Privacy-Preserving Method for converting Artificial Neural Networks to Spiking Neural Networks.- PoShapley-BCFL: A fair and robust decentralized federated learning based on blockchain and the proof of Shapley-value.- Small-World Echo State Networks for Nonlinear Time-Series Prediction.- Preserving Potential Neighbors for Low-Degree Nodes via Reweighting in Link Prediction.- 6D Object Pose Estimation with Attention Aware Bi-Gated Fusion.