We present network embedding algorithms that capture information about a node from the
local distribution over node attributes around it, as observed over random walks following an …

Recent works have argued that high-level semantic concepts are encoded" linearly" in the
representation space of large language models. In this work, we study the origins of such …

The skip-gram model for learning word embeddings (Mikolov et al. 2013) has been widely
popular, and DeepWalk (Perozzi et al. 2014), among other methods, has extended the …

Product embeddings have been heavily investigated in the past few years, serving as the
cornerstone for a broad range of machine learning applications in e-commerce. Despite the …

Despite the recent popularity of contextual word embeddings, static word embeddings still
dominate lexical semantic tasks, making their study of continued relevance. A widely …

Many models learn representations of knowledge graph data by exploiting its low-rank latent
structure, encoding known relations between entities and enabling unknown facts to be …

The key to vertex embedding is to learn low-dimensional representations of global graph
information, and integrating information from multiple steps is an effective strategy. Existing …

Numbers in spreadsheets often have units: metres, grams, dollars, etc. Spreadsheet cells
typically cannot carry unit information, and even where they can, users may not be motivated …

Many methods have been developed to represent knowledge graph data, which implicitly
exploit low-rank latent structure in the data to encode known information and enable …

The word embedding models such as Word2vec and FastText simultaneously learn dual
representations of input vectors and output vectors. In contrast, almost all existing …