Read more
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.
List 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.
Summary
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.
