Portrait de Joey Bose

Joey Bose

Membre affilié
joey.bosr@gmail.com
University of Oxford, Département d'informatique
Sujets de recherche
Apprentissage profond
Apprentissage profond géométrique
IA pour la science
Modèles génératifs
Modélisation moléculaire
Site web
Google Scholar
X

Publications

Riemannian Diffusion Models
Chin-Wei Huang
Milad Aghajohari
Joey Bose
Prakash Panangaden
Aaron Courville
Diffusion models are recent state-of-the-art methods for image generation and likelihood estimation. In this work, we generalize continuous-… (voir plus)time diffusion models to arbitrary Riemannian manifolds and derive a variational framework for likelihood estimation. Computationally, we propose new methods for computing the Riemannian divergence which is needed for likelihood estimation. Moreover, in generalizing the Euclidean case, we prove that maximizing this variational lower-bound is equivalent to Riemannian score matching. Empirically, we demonstrate the expressive power of Riemannian diffusion models on a wide spectrum of smooth manifolds, such as spheres, tori, hyperboloids, and orthogonal groups. Our proposed method achieves new state-of-the-art likelihoods on all benchmarks.
openreview.net
A Cross-Domain Transferable Neural Coherence Model
Peng Xu
H. Saghir
Jin Sung Kang
Teng Long
Joey Bose
Yanshuai Cao
Jackie Cheung
Coherence is an important aspect of text quality and is crucial for ensuring its readability. One important limitation of existing coherence… (voir plus) models is that training on one domain does not easily generalize to unseen categories of text. Previous work advocates for generative models for cross-domain generalization, because for discriminative models, the space of incoherent sentence orderings to discriminate against during training is prohibitively large. In this work, we propose a local discriminative neural model with a much smaller negative sampling space that can efficiently learn against incorrect orderings. The proposed coherence model is simple in structure, yet it significantly outperforms previous state-of-art methods on a standard benchmark dataset on the Wall Street Journal corpus, as well as in multiple new challenging settings of transfer to unseen categories of discourse on Wikipedia articles.
2019-07-01
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (publié)
doi.org
arxiv.org