Conformal retrofitting via Riemannian manifolds: distilling task-specific graphs into pretrained embeddings

• URL: http://arxiv.org/abs/2010.04842v1
• Date: Fri, 9 Oct 2020 23:06:57 GMT
• Title: Conformal retrofitting via Riemannian manifolds: distilling task-specific graphs into pretrained embeddings
• Authors: Justin Dieter and Arun Tejasvi Chaganty
• Abstract summary: Pretrained embeddings are versatile, task-agnostic feature representations of entities, like words, that are central to many machine learning applications. Existing retrofitting algorithms face two limitations: they overfit the observed graph by failing to represent relationships with missing entities. We propose a novel regularizer, a conformality regularizer, that preserves local geometry from the pretrained embeddings, and a new feedforward layer that learns to map pre-trained embeddings onto a non-Euclidean manifold.
• Score: 1.2970250708769708
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Pretrained (language) embeddings are versatile, task-agnostic feature representations of entities, like words, that are central to many machine learning applications. These representations can be enriched through retrofitting, a class of methods that incorporate task-specific domain knowledge encoded as a graph over a subset of these entities. However, existing retrofitting algorithms face two limitations: they overfit the observed graph by failing to represent relationships with missing entities; and they underfit the observed graph by only learning embeddings in Euclidean manifolds, which cannot faithfully represent even simple tree-structured or cyclic graphs. We address these problems with two key contributions: (i) we propose a novel regularizer, a conformality regularizer, that preserves local geometry from the pretrained embeddings---enabling generalization to missing entities and (ii) a new Riemannian feedforward layer that learns to map pre-trained embeddings onto a non-Euclidean manifold that can better represent the entire graph. Through experiments on WordNet, we demonstrate that the conformality regularizer prevents even existing (Euclidean-only) methods from overfitting on link prediction for missing entities, and---together with the Riemannian feedforward layer---learns non-Euclidean embeddings that outperform them.

Related papers

• Improving embedding of graphs with missing data by soft manifolds [51.425411400683565]
  The reliability of graph embeddings depends on how much the geometry of the continuous space matches the graph structure. We introduce a new class of manifold, named soft manifold, that can solve this situation. Using soft manifold for graph embedding, we can provide continuous spaces to pursue any task in data analysis over complex datasets.
  arXiv  Detail & Related papers  (2023-11-29T12:48:33Z)
• Semi-Supervised Manifold Learning with Complexity Decoupled Chart Autoencoders [45.29194877564103]
  This work introduces a chart autoencoder with an asymmetric encoding-decoding process that can incorporate additional semi-supervised information such as class labels. We discuss the approximation power of such networks and derive a bound that essentially depends on the intrinsic dimension of the data manifold rather than the dimension of ambient space.
  arXiv  Detail & Related papers  (2022-08-22T19:58:03Z)
• Repurposing Knowledge Graph Embeddings for Triple Representation via Weak Supervision [77.34726150561087]
  Current methods learn triple embeddings from scratch without utilizing entity and predicate embeddings from pre-trained models. We develop a method for automatically sampling triples from a knowledge graph and estimating their pairwise similarities from pre-trained embedding models. These pairwise similarity scores are then fed to a Siamese-like neural architecture to fine-tune triple representations.
  arXiv  Detail & Related papers  (2022-08-22T14:07:08Z)
• Counterfactual Intervention Feature Transfer for Visible-Infrared Person Re-identification [69.45543438974963]
  We find graph-based methods in the visible-infrared person re-identification task (VI-ReID) suffer from bad generalization because of two issues. The well-trained input features weaken the learning of graph topology, making it not generalized enough during the inference process. We propose a Counterfactual Intervention Feature Transfer (CIFT) method to tackle these problems.
  arXiv  Detail & Related papers  (2022-08-01T16:15:31Z)
• Geometry Contrastive Learning on Heterogeneous Graphs [50.58523799455101]
  This paper proposes a novel self-supervised learning method, termed as Geometry Contrastive Learning (GCL) GCL views a heterogeneous graph from Euclidean and hyperbolic perspective simultaneously, aiming to make a strong merger of the ability of modeling rich semantics and complex structures. Extensive experiments on four benchmarks data sets show that the proposed approach outperforms the strong baselines.
  arXiv  Detail & Related papers  (2022-06-25T03:54:53Z)
• Classic Graph Structural Features Outperform Factorization-Based Graph Embedding Methods on Community Labeling [8.931361895613646]
  Graph representation learning (also called graph embeddings) is a popular technique for incorporating network structure into machine learning models. We provide an empirical and theoretical analysis for the performance of a class of embeddings on the common task of pairwise community labeling. We prove that popular low-dimensional factorization methods either cannot produce community structure, or can only produce unstable" communities.
  arXiv  Detail & Related papers  (2022-01-20T22:43:37Z)
• A Self-supervised Mixed-curvature Graph Neural Network [76.3790248465522]
  We present a novel Self-supervised Mixed-curvature Graph Neural Network (SelfMGNN) We show that SelfMGNN captures the complicated graph structures in reality and outperforms state-of-the-art baselines.
  arXiv  Detail & Related papers  (2021-12-10T08:56:55Z)
• Asymptotics of Network Embeddings Learned via Subsampling [4.23373349945751]
  We study representation methods using a subsampling approach, such as node2vec, into a single unifying framework. This provides a theoretical foundation to understand what the embedding vectors represent and how well these methods perform on downstream tasks. Notably, we observe that typically used loss functions may lead to shortcomings, such as a lack of Fisher consistency.
  arXiv  Detail & Related papers  (2021-07-06T02:54:53Z)
• Learning the Implicit Semantic Representation on Graph-Structured Data [57.670106959061634]
  Existing representation learning methods in graph convolutional networks are mainly designed by describing the neighborhood of each node as a perceptual whole. We propose a Semantic Graph Convolutional Networks (SGCN) that explores the implicit semantics by learning latent semantic-paths in graphs.
  arXiv  Detail & Related papers  (2021-01-16T16:18:43Z)
• Computationally Tractable Riemannian Manifolds for Graph Embeddings [10.420394952839242]
  We show how to learn and optimize graph embeddings in certain curved Riemannian spaces. Our results serve as new evidence for the benefits of non-Euclidean embeddings in machine learning pipelines.
  arXiv  Detail & Related papers  (2020-02-20T10:55:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.