Related papers: HaSa: Hardness and Structure-Aware Contrastive Kno…

Knowledge amalgamation (KA) aims to learn a compact student model to handle the joint objective from multiple teacher models that are are specialized for their own tasks respectively. Current methods focus on coarsely aligning teachers and…

Negative sampling, which samples negative triplets from non-observed ones in knowledge graph (KG), is an essential step in KG embedding. Recently, generative adversarial network (GAN), has been introduced in negative sampling. By sampling…

Knowledge graph completion (KGC) tasks aim to infer missing facts in a knowledge graph (KG) for many knowledge-intensive applications. However, existing embedding-based KGC approaches primarily rely on factual triples, potentially leading…

InfoNCE loss is a widely used loss function for contrastive model training. It aims to estimate the mutual information between a pair of variables by discriminating between each positive pair and its associated $K$ negative pairs. It is…

Knowledge Graph Embedding (KGE) has proven to be an effective approach to solving the Knowledge Graph Completion (KGC) task. Relational patterns which refer to relations with specific semantics exhibiting graph patterns are an important…

Knowledge representation learning aims at modeling knowledge graph by encoding entities and relations into a low dimensional space. Most of the traditional works for knowledge embedding need negative sampling to minimize a margin-based…

Recently, several Knowledge Graph Embedding (KGE) approaches have been devised to represent entities and relations in dense vector space and employed in downstream tasks such as link prediction. A few KGE techniques address…

Contrastive learning has become a cornerstone of modern representation learning, allowing training with massive unlabeled data for both task-specific and general (foundation) models. A prototypical loss in contrastive training is InfoNCE…

Knowledge graphs (KGs) that modelings the world knowledge as structural triples are inevitably incomplete. Such problems still exist for multimodal knowledge graphs (MMKGs). Thus, knowledge graph completion (KGC) is of great importance to…

Recently, Hyper-relational Knowledge Graphs (HKGs) have been proposed as an extension of traditional Knowledge Graphs (KGs) to better represent real-world facts with additional qualifiers. As a result, researchers have attempted to adapt…

Knowledge Graphs (KGs) provide a structured representation of knowledge but often suffer from challenges of incompleteness. To address this, link prediction or knowledge graph completion (KGC) aims to infer missing new facts based on…

Knowledge graph embedding (KGE) is an increasingly popular technique that aims to represent entities and relations of knowledge graphs into low-dimensional semantic spaces for a wide spectrum of applications such as link prediction,…

Unsupervised sentence representation learning remains a critical challenge in modern natural language processing (NLP) research. Recently, contrastive learning techniques have achieved significant success in addressing this issue by…

Knowledge Graph Embedding (KGE) transforms a discrete Knowledge Graph (KG) into a continuous vector space facilitating its use in various AI-driven applications like Semantic Search, Question Answering, or Recommenders. While KGE approaches…

Recent trends in NLP utilize knowledge graphs (KGs) to enhance pretrained language models by incorporating additional knowledge from the graph structures to learn domain-specific terminology or relationships between documents that might…

Heterogeneous graph neural networks (HGNNs) as an emerging technique have shown superior capacity of dealing with heterogeneous information network (HIN). However, most HGNNs follow a semi-supervised learning manner, which notably limits…

Knowledge graph embedding (KGE), aiming to embed entities and relations into low-dimensional vectors, has attracted wide attention recently. However, the existing research is mainly based on the black-box neural models, which makes it…

Knowledge graph completion (KGC) focuses on identifying missing triples in a knowledge graph (KG) , which is crucial for many downstream applications. Given the rapid development of large language models (LLMs), some LLM-based methods are…

In recent years, Knowledge Graph (KG) development has attracted significant researches considering the applications in web search, relation prediction, natural language processing, information retrieval, question answering to name a few.…

Knowledge representation learning has received a lot of attention in the past few years. The success of existing methods heavily relies on the quality of knowledge graphs. The entities with few triplets tend to be learned with less…