相关论文: Unlearning of Knowledge Graph Embedding via Prefer…

Embedding knowledge graphs (KGs) into continuous vector spaces is a focus of current research. Early works performed this task via simple models developed over KG triples. Recent attempts focused on either designing more complicated triple…

Embedding models have shown great power in knowledge graph completion (KGC) task. By learning structural constraints for each training triple, these methods implicitly memorize intrinsic relation rules to infer missing links. However, this…

Direct Preference Optimization (DPO) has been proposed as an effective and efficient alternative to reinforcement learning from human feedback (RLHF). However, neither RLHF nor DPO take into account the fact that learning certain…

Advancing AI systems in scientific domains like physics, materials science, and engineering calls for reasoning over complex, multi-physics phenomena while respecting governing principles. Although Large Language Models (LLMs) and existing…

Knowledge Graphs (KGs), representing facts as triples, have been widely adopted in many applications. Reasoning tasks such as link prediction and rule induction are important for the development of KGs. Knowledge Graph Embeddings (KGEs)…

Knowledge Graphs (KGs) have found many applications in industry and academic settings, which in turn, have motivated considerable research efforts towards large-scale information extraction from a variety of sources. Despite such efforts,…

As concerns over data privacy intensify, unlearning in Graph Neural Networks (GNNs) has emerged as a prominent research frontier in academia. This concept is pivotal in enforcing the \textit{right to be forgotten}, which entails the…

Knowledge graph (KG) embedding encodes the entities and relations from a KG into low-dimensional vector spaces to support various applications such as KG completion, question answering, and recommender systems. In real world, knowledge…

The recent proliferation of knowledge graphs (KGs) coupled with incomplete or partial information, in the form of missing relations (links) between entities, has fueled a lot of research on knowledge base completion (also known as relation…

Previous knowledge graph embedding approaches usually map entities to representations and utilize score functions to predict the target entities, yet they typically struggle to reason rare or emerging unseen entities. In this paper, we…

Machine Learning has been the quintessential solution for many AI problems, but learning is still heavily dependent on the specific training data. Some learning models can be incorporated with a prior knowledge in the Bayesian set up, but…

Knowledge Graph Embedding (KGE) aims to represent entities and relations of knowledge graph in a low-dimensional continuous vector space. Recent works focus on incorporating structural knowledge with additional information, such as entity…

Learning the embeddings of knowledge graphs (KG) is vital in artificial intelligence, and can benefit various downstream applications, such as recommendation and question answering. In recent years, many research efforts have been proposed…

Continual Knowledge Graph Embedding (CKGE) aims to efficiently learn new knowledge and simultaneously preserve old knowledge. Dominant approaches primarily focus on alleviating catastrophic forgetting of old knowledge but neglect efficient…

In the last few years, the solution to Knowledge Graph (KG) completion via learning embeddings of entities and relations has attracted a surge of interest. Temporal KGs(TKGs) extend traditional Knowledge Graphs (KGs) by associating static…

Knowledge graphs represent information as structured triples and serve as the backbone for a wide range of applications, including question answering, link prediction, and recommendation systems. A prominent line of research for exploring…

The growing enforcement of the right to be forgotten regulations has propelled recent advances in certified (graph) unlearning strategies to comply with data removal requests from deployed machine learning (ML) models. Motivated by the…

DPO (Direct Preference Optimization) has become a widely used offline preference optimization algorithm due to its simplicity and training stability. However, DPO is prone to overfitting and collapse. To address these challenges, we propose…

Unlearning knowledge is a pressing and challenging task in Large Language Models (LLMs) because of their unprecedented capability to memorize and digest training data at scale, raising more significant issues regarding safety, privacy, and…

Recent advances in research have demonstrated the effectiveness of knowledge graphs (KG) in providing valuable external knowledge to improve recommendation systems (RS). A knowledge graph is capable of encoding high-order relations that…