The Immersion of Directed Multi-graphs in Embedding Fields. Generalisations
This provides a generalised model for cross-domain queries and functions in machine learning applications like computer vision and NLP, though it appears incremental as it builds on existing embedding and graph-based methods.
The paper tackles the problem of representing diverse data types (relational-categorical, symbolic, perceptual-sensory, perceptual-latent) in a unified architectural layer, achieving this by using a directed Tensor-Typed Multi-Graph with edge attributes to define similarity and distance relationships across tensorial forms.
The purpose of this paper is to outline a generalised model for representing hybrids of relational-categorical, symbolic, perceptual-sensory and perceptual-latent data, so as to embody, in the same architectural data layer, representations for the input, output and latent tensors. This variety of representation is currently used by various machine-learning models in computer vision, NLP/NLU, reinforcement learning which allows for direct application of cross-domain queries and functions. This is achieved by endowing a directed Tensor-Typed Multi-Graph with at least some edge attributes which represent the embeddings from various latent spaces, so as to define, construct and compute new similarity and distance relationships between and across tensorial forms, including visual, linguistic, auditory latent representations, thus stitching the logical-categorical view of the observed universe to the Bayesian/statistical view.