Neural Information Processing [electronic resource] : 29th International Conference, ICONIP 2022, Virtual Event, November 22–26, 2022, Proceedings, Part I /

Theory and Algorithms -- Solving Partial Differential Equations using Point-based Neural Networks -- Patch Mix Augmentation with Dual Encoders for Meta-Learning -- Tacit Commitments Emergence in Multi-agent Reinforcement Learning -- Saccade Direction Information Channel -- Shared-Attribute Multi-Graph Clustering with Global Self-Attention -- Mutual Diverse-Label Adversarial Training -- Multi-Agent Hyper-Attention Policy Optimization -- Filter Pruning via Similarity Clustering for Deep Convolutional Neural Networks -- FPD: Feature Pyramid Knowledge Distillation -- An effective ensemble model related to incremental learning in neural machine translation -- Local-Global Semantic Fusion Single-shot Classification Method -- Self-Reinforcing Feedback Domain Adaptation Channel -- General Algorithm for Learning from Grouped Uncoupled Data and Pairwise Comparison Data -- Additional Learning for Joint Probability Distribution Matching in BiGAN -- Multi-View Self-Attention for Regression Domain Adaptation with Feature Selection -- EigenGRF: Layer-Wise Eigen-Learning for Controllable Generative Radiance Fields -- Partial Label learning with Gradually Induced Error-Correction Output Codes -- HMC-PSO: A Hamiltonian Monte Carlo and Particle Swarm Optimization-based optimizer -- Heterogeneous Graph Representation for Knowledge Tracing -- Intuitionistic fuzzy universum support vector machine -- Support vector machine based models with sparse auto-encoder based features for classification problem -- Selectively increasing the diversity of GAN-generated samples -- Cooperation and Competition: Flocking with Evolutionary Multi-Agent Reinforcement Learning -- Differentiable Causal Discovery Under Heteroscedastic Noise -- IDPL: Intra-subdomain adaptation adversarial learning segmentation method based on Dynamic Pseudo Labels -- Adaptive Scaling for U-Net in Time Series Classification -- Permutation Elementary Cellular Automata: Analysis and Application of Simple Examples -- SSPR: A Skyline-Based Semantic Place Retrieval Method -- Double Regularization-based RVFL and edRVFL Networks for Sparse-Dataset Classification -- Adaptive Tabu Dropout for Regularization of Deep Neural Networks -- Class-Incremental Learning with Multiscale Distillation for Weakly Supervised Temporal Action Localization -- Nearest Neighbor Classifier with Margin Penalty for Active Learning -- Factual Error Correction in Summarization with Retriever-Reader Pipeline -- Context-adapted Multi-policy Ensemble Method for Generalization in Reinforcement Learning -- Self-attention based multi-scale graph convolutional networks -- Synesthesia Transformer with Contrastive Multimodal Learning -- Context-based Point Generation Network for Point Cloud Completion -- Temporal Neighborhood Change Centrality for Important Node Identification in Temporal Networks -- DOM2R-Graph: A Web Attribute Extraction Architecture with Relation-aware Heterogeneous Graph Transformer -- Sparse Linear Capsules for Matrix Factorization-based Collaborative Filtering -- PromptFusion: a Low-cost Prompt-based Task Composition for Multi-task Learning -- A fast and efficient algorithm for filtering the training dataset -- Entropy-minimization Mean Teacher for Source-Free Domain Adaptive Object Detection -- IA-CL: A Deep Bidirectional Competitive Learning Method for Traveling Salesman Problem -- Boosting Graph Convolutional Networks With Semi-Supervised Training -- Auxiliary Network: Scalable and agile online learning for dynamic system with inconsistently available inputs -- VAAC: V-value Attention Actor-Critic for Cooperative Multi-agent Reinforcement Learning -- An Analytical Estimation of Spiking Neural Networks Energy Efficiency -- Correlation Based Semantic Transfer with Application to Domain Adaptation -- Minimum Variance Embedded Intuitionistic Fuzzy Weighted Random Vector Functional Link Network -- Neural Network Compression by Joint Sparsity Promotion and Redundancy Reduction.

The three-volume set LNCS 13623, 13624, and 13625 constitutes the refereed proceedings of the 29th International Conference on Neural Information Processing, ICONIP 2022, held as a virtual event, November 22–26, 2022. The 146 papers presented in the proceedings set were carefully reviewed and selected from 810 submissions. They were organized in topical sections as follows: Theory and Algorithms; Cognitive Neurosciences; Human Centered Computing; and Applications. The ICONIP conference aims to provide a leading international forum for researchers, scientists, and industry professionals who are working in neuroscience, neural networks, deep learning, and related fields to share their new ideas, progress, and achievements.