Anomaly Detection in Directed Dynamic Graphs via RDGCN and LSTAN -- Anomaly-Based Insider Threat Detection via Hierarchical Information Fusion -- CSEDesc: CyberSecurity Event Detection with Event Description -- GanNeXt: A New Convolutional GAN for Anomaly Detection -- K-Fold Cross-Valuation for Machine Learning Using Shapley Value -- Malicious Domain Detection Based on Self-supervised HGNNs with Contrastive Learning -- Time Series Anomaly Detection with Reconstruction-Based State-Space Models -- ReDualSVG: Refined Scalable Vector Graphics Generation -- Rethinking Feature Context in Learning Image-guided Depth Completion -- Semantic and Frequency Representation Mining for Face Manipulation Detection -- Single image dehazing network based on serial feature attention -- SS-Net: 3D Spatial-Spectral Network for Cerebrovascular Segmentation in TOF-MRA -- STAN: Spatio-Temporal Alignment Network for No-Reference Video Quality Assessment -- Style Expansion without Forgetting for Handwritten Character Recognition -- TransVQ-VAE: Generating Diverse Images using Hierarchical Representation Learning -- UG-Net: Unsupervised-Guided Network for Biomedical Image Segmentation and Classification -- Unsupervised Shape Enhancement and Factorization Machine Network for 3D Face Reconstruction -- Visible-Infrared Person Re-Identification via Modality Augmentation and Center Constraints -- Water Conservancy Remote Sensing Image Classification Based on Target-Scene Deep Semantic Enhancement -- A Partitioned Detection Architecture for Oriented Objects -- A Personalized Federated Multi-Task Learning Scheme for Encrypted Traffic Classification -- Addressing delays in Reinforcement Learning via Delayed Adversarial Imitation Learning -- An Evaluation of Self-Supervised Learning for Portfolio Diversification -- An exploitation-enhanced Bayesian optimization algorithm for high-dimensional expensive problems -- Balancing Selection and Diversity in Ensemble Learning with Exponential Mixture Model -- CIPER: Combining Invariant and Equivariant Representations Using Contrastive and Predictive Learning -- Contrastive Learning and the Emergence of Attributes Associations -- Contrastive Learning for Sleep Staging based on Inter Subject Correlation -- Diffusion Policies as Multi-Agent Reinforcement Learning Strategies -- Dynamic Memory-based Continual Learning with Generating and Screening -- Enhancing Text2SQL Generation with Syntactic Infor-mation and Multi-Task Learning -- Fast Generalizable Novel View Synthesis with Uncertainty-Aware Sampling -- Find Important Training Dataset by Observing the Training Sequence Similarity -- Generating Question-Answer Pairs for Few-shot Learning -- GFedKRL: Graph Federated Knowledge Re-Learning for Effective Molecular Property Prediction via Privacy Protection -- Gradient-Boosted Based Structured and UnstructuredLearning -- Graph Federated Learning Based on the Decentralized Framework -- Heterogeneous Federated Learning Based on Graph Hypernetwork -- Learning to Resolve Conflicts in Multi-Task Learning -- Neighborhood-oriented Decentralized Learning Communication in Multi-Agent System -- NN-Denoising: A Low-Noise Distantly Supervised Document-Level Relation Extraction Scheme using Natural Language Inference and Negative Sampling -- pFedLHNs: Personalized Federated Learning via Local Hypernetworks -- Prototype Contrastive Learning for Personalized Federated Learning -- PTSTEP: Prompt Tuning for Semantic Typing of Event Processes -- SR-IDS: A Novel Network Intrusion Detection System Based on Self-taught Learning and Representation Learning -- Task-Aware Adversarial Feature Perturbation for Cross-Domain Few-Shot Learning -- Ternary Data, Triangle Decoding, Three Tasks, a Multitask Learning Speech Translation Model.

The 10-volume set LNCS 14254-14263 constitutes the proceedings of the 32nd International Conference on Artificial Neural Networks and Machine Learning, ICANN 2023, which took place in Heraklion, Crete, Greece, during September 26-29, 2023. The 426 full papers, 9 short papers and 9 abstract papers included in these proceedings were carefully reviewed and selected from 947 submissions. ICANN is a dual-track conference, featuring tracks in brain inspired computing on the one hand, and machine learning on the other, with strong cross-disciplinary interactions and applications. .