Hyperbolic Disk Embeddings for Directed Acyclic Graphs
Obtaining continuous representations of structural data such as directed acyclic graphs (DAGs) has gained attention in machine learning and artificial intelligence. However, embedding complex DAGs in which both ancestors and descendants of nodes are exponentially increasing is difficult. Tackling in this problem, we develop Disk Embeddings, which is a framework for embedding DAGs into quasi-metric spaces. Existing state-of-the-art methods, Order Embeddings and Hyperbolic Entailment Cones, are instances of Disk Embedding in Euclidean space and spheres respectively. Furthermore, we propose a novel method Hyperbolic Disk Embeddings to handle exponential growth of relations. The results of our experiments show that our Disk Embedding models outperform existing methods especially in complex DAGs other than trees.
Code (2)
Similar Papers 제목 키워드 기반
An in-depth look at Euclidean disk embeddings for structure preserving parsing
Preserving the structural properties of trees or graphs when embedding them into a metric space allows for a high degree of interpretability, and has been shown beneficial for downstream tasks (e.g., hypernym detection, …
Dependency ParsingNatural Language InferenceRetrievalSemantic ParsingHyperbolic Entailment Cones for Learning Hierarchical Embeddings
Learning graph representations via low-dimensional embeddings that preserve relevant network properties is an important class of problems in machine learning. We here present a novel method to embed directed acyclic grap…
Graph EmbeddingHypernym DiscoveryLink PredictionRepresentation LearningShadow Cones: A Generalized Framework for Partial Order Embeddings
Hyperbolic space has proven to be well-suited for capturing hierarchical relations in data, such as trees and directed acyclic graphs. Prior work introduced the concept of entailment cones, which uses partial orders defi…
D-HYPR: Harnessing Neighborhood Modeling and Asymmetry Preservation for Digraph Representation Learning
Digraph Representation Learning (DRL) aims to learn representations for directed homogeneous graphs (digraphs). Prior work in DRL is largely constrained (e.g., limited to directed acyclic graphs), or has poor generalizab…
Link PredictionLink Property PredictionNode ClassificationProperty Prediction+1Capacity and Bias of Learned Geometric Embeddings for Directed Graphs
A wide variety of machine learning tasks such as knowledge base completion, ontology alignment, and multi-label classification can benefit from incorporating into learning differentiable representations of graphs or taxo…
Knowledge Base CompletionMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATION