Neural Information Processing: 29th International Conference, ICONIP 2022, Virtual Event, November 22–26, 2022, Proceedings, Part IV

The four-volume set CCIS 1791, 1792, 1793 and 1794 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 213 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.

Table of Contents:
​Theory and Algorithms.- Knowledge Transfer from Situation Evaluation to Multi-agent Reinforcement Learning.- Sequential three-way rules class-overlap under-sampling based on fuzzy hierarchical subspace for imbalanced data.- Two-stage Multilayer Perceptron Hawkes Process.- The Context Hierarchical Contrastive Learning for Time Series in Frequency Domain.- Hawkes Process via Graph Contrastive Discriminant representation Learning and Transformer capturing long-term dependencies.- A Temporal Consistency Enhancement Algorithm Based On Pixel Flicker Correction.- Data representation and clustering with double low-rank constraints.- RoMA: a Method for Neural Network Robustness Measurement and Assessment.- Independent Relationship Detection for Real-Time Scene Graph Generation.- A multi-label feature selection method based on feature graph with ridge regression and eigenvector centrality.- O3GPT: A Guidance-Oriented Periodic Testing Framework with Online Learning, Online Testing,and Online Feedback.- AFFSRN: Attention-Based Feature Fusion Super-Resolution Network.- Temporal-Sequential Learning with Columnar-Structured Spiking Neural Networks.- Graph Attention Transformer Network for Robust Visual Tracking.- GCL-KGE:Graph Contrastive Learning for Knowledge Graph Embedding.- Towards a Unified Benchmark for Reinforcement Learning in Sparse Reward Environments.- Effect of Logistic Activation Function and Multiplicative Input Noise on DNN-kWTA model.- A High-Speed SSVEP-Based Speller Using Continuous Spelling Method.- AAT: Non-Local Networks for Sim-to-Real Adversarial Augmentation Transfer.- Aggregating Intra-class and Inter-class information for Multi-label Text Classification.- Fast estimation of multidimensional regression functions by the Parzen kernel-based method.- ReGAE: Graph autoencoder based on recursive neural networks.- Efficient Uncertainty Quantification for Under-constraint Prediction following Learning using MCMC.- SMART: A Robustness Evaluation Framework for Neural Networks.- Time-aware Quaternion Convolutional Network for Temporal Knowledge Graph Reasoning.- SumBART - An improved BART model for abstractive text summarization.- Saliency-Guided Learned Image Compression for Object Detection.- Multi-Label Learning with Data Self-Augmentation.- MnRec: A News Recommendation Fusion Model Combining Multi-granularity Information.- Infinite Label Selection Method for Mutil-label Classification.- Simultaneous Perturbation Method for Multi-Task Weight Optimization in One-Shot Meta-Learning.- Searching for Textual Adversarial Examples with Learned Strategy.- Multivariate Time Series Retrieval with Binary Coding from Transformer. -Learning TSP Combinatorial Search and Optimization with Heuristic Search.- A Joint Learning Model for Open Set Recognition with Post-processing.- Cross-Layer Fusion for Feature Distillation.- MCHPT: A Weakly Supervise Based Merchant Pre-trained Model.- Progressive Latent Replay for efficient Generative Rehearsal.- Generalization Bounds for Set-to-Set Matching with Negative Sampling.- ADA: An Attention-Based Data Augmentation Approach to Handle Imbalanced Textual Datasets.- Countering the Anti-detection Adversarial Attacks.- Evolving Temporal Knowledge Graphs by Iterative Spatio-Temporal Walks.- Improving Knowledge Graph Embedding Using Dynamic Aggregation of Neighbor Information.- Generative Generalized Zero-Shot Learning based on Auxiliary-Features.- Learning Stable Representations with Progressive Autoencoder (PAE).- Effect of Image Down-sampling on Detection of Adversarial Examples .- Boosting the Robustness of Neural Networks with M-PGD.- StatMix: Data augmentation method that relies on image statistics in federated learning.- Classification by Components Including Chow's Reject Option. -Community discovery algorithm based on improved deep sparse autoencoder.- Fairly Constricted Multi-Objective Particle Swarm Optimization.- Argument Classification with BERT plus Contextual, Structural andSyntactic Features as Text.- Variance Reduction for Deep Q-Learning using Stochastic Recursive Gradient.- Optimizing Knowledge Distillation Via Shallow Texture Knowledge Transfer.- Unsupervised Domain Adaptation Supplemented with Generated Images.- MAR2MIX: A Novel Model for Dynamic Problem in Multi-Agent Reinforcement Learning.- Adversarial Training with Knowledge Distillation Considering Intermediate Representations in CNNs.- Deep Contrastive Multi-view Subspace Clustering.