scispace - formally typeset
W

William Fedus

Researcher at Google

Publications -  43
Citations -  5202

William Fedus is an academic researcher from Google. The author has contributed to research in topics: Computer science & Reinforcement learning. The author has an hindex of 20, co-authored 33 publications receiving 2741 citations. Previous affiliations of William Fedus include Université de Montréal & Massachusetts Institute of Technology.

Papers
More filters
Posted Content

Deep Graph Infomax.

Petar Veličković, +5 more
- 27 Sep 2018 - 
TL;DR: Deep Graph Infomax (DGI) is presented, a general approach for learning node representations within graph-structured data in an unsupervised manner that is readily applicable to both transductive and inductive learning setups.
Proceedings ArticleDOI

Deep Graph Infomax

Petar Veličković, +5 more
TL;DR: Deep Graph Infomax (DGI) as discussed by the authors is a general approach for learning node representations within graph-structured data in an unsupervised manner, which relies on maximizing mutual information between patch representations and corresponding high-level summaries of graphs.
Journal ArticleDOI

Emergent Abilities of Large Language Models

Jason Loh Seong Wei, +15 more
TL;DR: The authors discusses an unpredictable phenomenon that is referred to as emergent abilities of large language models, i.e., an ability to be emergent if it is not present in smaller models but is present in larger models.
Journal ArticleDOI

In Silico Labeling: Predicting Fluorescent Labels in Unlabeled Images

Eric Christiansen, +20 more
- 19 Apr 2018 - 
TL;DR: It is shown that a computational machine-learning approach, which is called "in silico labeling" (ISL), reliably predicts some fluorescent labels from transmitted-light images of unlabeled fixed or live biological samples.
Journal Article

Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

Aarohi Srivastava, +439 more
- 09 Jun 2022 - 
TL;DR: Evaluation of OpenAI's GPT models, Google-internal dense transformer architectures, and Switch-style sparse transformers on BIG-bench, across model sizes spanning millions to hundreds of billions of parameters finds that model performance and calibration both improve with scale, but are poor in absolute terms.