Related papers: Relational Learning in Pre-Trained Models: A Theor…

Despite the advances in large language models (LLMs), how they use their knowledge for reasoning is not yet well understood. In this study, we propose a method that deconstructs complex real-world questions into a graph, representing each…

Pretraining reinforcement learning (RL) models on offline datasets is a promising way to improve their training efficiency in online tasks, but challenging due to the inherent mismatch in dynamics and behaviors across various tasks. We…

Large language models (LLMs) have recently shown strong potential in modeling relational structures. However, existing approaches remain fundamentally graph-centric: they focus on processing pairwise graph structures into tokens that LLMs…

Most language models (LMs) are trained and applied in an autoregressive left-to-right fashion, assuming that the next token only depends on the preceding ones. However, this assumption ignores the potential benefits of using the full…

Hypergraphs play a pivotal role in the modelling of data featuring higher-order relations involving more than two entities. Hypergraph neural networks emerge as a powerful tool for processing hypergraph-structured data, delivering…

Deep learning methods capable of handling relational data have proliferated over the last years. In contrast to traditional relational learning methods that leverage first-order logic for representing such data, these deep learning methods…

Machine Unlearning has emerged as a significant area of research, focusing on `removing' specific subsets of data from a trained model. Fine-tuning (FT) methods have become one of the fundamental approaches for approximating unlearning, as…

We present a novel methodology to jointly perform multi-task learning and infer intrinsic relationship among tasks by an interpretable and sparse graph. Unlike existing multi-task learning methodologies, the graph structure is not assumed…

Graph neural networks (GNNs) are shown to be successful in modeling applications with graph structures. However, training an accurate GNN model requires a large collection of labeled data and expressive features, which might be inaccessible…

Emotion recognition is relevant in various domains, ranging from healthcare to human-computer interaction. Physiological signals, being beyond voluntary control, offer reliable information for this purpose, unlike speech and facial…

Multi-step retrieval-augmented generation (RAG) has become a widely adopted strategy for enhancing large language models (LLMs) on tasks that demand global comprehension and intensive reasoning. Although many RAG systems incorporate a…

Foundation models have emerged as critical components in a variety of artificial intelligence applications, and showcase significant success in natural language processing and several other domains. Meanwhile, the field of graph machine…

With increasing privacy concerns on data, recent studies have made significant progress using federated learning (FL) on privacy-sensitive natural language processing (NLP) tasks. Much literature suggests fully fine-tuning pre-trained…

Process theories combine a graphical language for compositional reasoning with an underlying categorical semantics. They have been successfully applied to fields such as quantum computation, natural language processing, linear dynamical…

Multimodal data, which can comprehensively perceive and recognize the physical world, has become an essential path towards general artificial intelligence. However, multimodal large models trained on public datasets often underperform in…

Foundation models (FMs) have emerged as a transformative paradigm in medical image analysis, offering the potential to provide generalizable, task-agnostic solutions across a wide range of clinical tasks and imaging modalities. Their…

Federated learning (FL) has emerged as a promising paradigm for enabling the collaborative training of models without centralized access to the raw data on local devices. In the typical FL paradigm (e.g., FedAvg), model weights are sent to…

Real-world multimodal data usually exhibit complex structural relationships beyond traditional one-to-one mappings like image-caption pairs. Entities across modalities interact in intricate ways, with images and text forming diverse…

Perceptual features (PFs) have been used with great success in tasks such as transfer learning, style transfer, and super-resolution. However, the efficacy of PFs as key source of information for learning generative models is not well…

Classical federated learning (FL) enables training machine learning models without sharing data for privacy preservation, but heterogeneous data characteristic degrades the performance of the localized model. Personalized FL (PFL) addresses…