Artificial Neural Networks and Machine Learning – ICANN 2025: 34th International Conference on Artificial Neural Networks, Kaunas, Lithuania, September 9–12, 2025, Proceedings, Part III(16070 Lecture Notes in Computer Science)

The four-volume set LNCS 16068-16071 constitutes the proceedings of the 34th International Conference on Artificial Neural Networks and Machine Learning, ICANN 2025, held in Kaunas, Lithuania, September 9–12, 2025. The 170 full papers and 8 abstracts included in these conference proceedings were carefully reviewed and selected from 375 submissions. The conference strongly values the synergy between theoretical progress and impactful real-world applications, and actively encourages contributions that demonstrate how artificial neural networks are being used to address pressing societal and technological challenges.

Table of Contents:
.- ACGCN: A Sequence-Attention-Based Graph Convolutional Model for Enhanced Recommendation Systems. .- Hyperparameter-Free Bi-Level Knowledge Graph Optimization for Link Prediction. .- SWIFT: State-space Wavelet Integrated Forecasting Technology for Enhanced Time Series Prediction. .- Federated Privacy-Preserving for Cross-Domain Sequential Recommendation. .- An Enhanced Audio Feature Tailored for Anomalous Sound Detection Based on Pre-trained Models. .- Multimodal Sentiment Analysis with Parallel Attention and Correlation Fusion. .- A Hybrid Learning Approach for Continual Knowledge Graph Embedding: Contrastive Masking and Joint Anti-Forgetting. .- Leveraging Machine-Translated Data for Sentiment Analysis in Low-Resource Languages: A Case Study on Bengal. .- RRetFC: Leveraging Recursive Retrieval For LLM-Enhanced Complex Fact-Checking. .- Feature-Aware Sequence Models for Tabular Data Processing with Missing Values. .- Topic-Driven Hyper-Relational Knowledge Graphs with Adaptive Reconstruction for Multi-Hop Question Answering Using LLMs. .- Toward Better Document-Level Relation Extraction: De-Sampling and Mixture of Experts in Action. .- ConSens: Assessing context grounding in open-book question answering. .- ChiMDQA: Towards Comprehensive Chinese Document QA with Fine-grained Evaluation. .- Emotional Text-to-Speech via Style Decoder with Emotion Shared Styleformer Block and RoPE Prior Encoder. .- Can LLM-Generated Textual Explanations Enhance Model Classification Performance? An Empirical Study. .- Early Acoustic and Vision Cross-modal Interation Learning for Multimal Sentiment Analysis. .- Uncovering Causal Relation Shifts in Event Sequences under Out-of-Domain Interventions. .- Sustainable techniques to improve Data Quality for training image-based explanatory models for Recommender Systems. .- TimeFlowDiffuser: A Hierarchical Diffusion Framework with Adaptive Context Sampling for Multi-Horizon Time Series Forecasting. .- ConDTab: Conditional Diffusion Transformer for Mixed-Type Tabular Synthesis with Dual Attention Latent Encoding. .- SentiAug: Adaptive Keywords Replacement and Confidence-guided Self-training Selection for Robust Sentiment Classification. .- Real-time and personalized product recommendations for large e-commerce platforms. .- A Two-Stage Framework Integrating Prompt Learning and Fine-tuning for Code Summarization. .- DialGACL: Nonlinear Graph Attention Reasoning with Contrastive Learning for Complex Dialogue Fact Verification. .- TimbreAdv: Timbre Adversarial Attacks on Speaker Verification Systems. .- Time Series Generation for Augmenting Multi-Channel Automotive Audio Data. .- PGD: Probe Guided Decoding for Alignment.