R
Ruslan Salakhutdinov
Researcher at Carnegie Mellon University
Publications - 457
Citations - 142495
Ruslan Salakhutdinov is an academic researcher from Carnegie Mellon University. The author has contributed to research in topics: Computer science & Artificial neural network. The author has an hindex of 107, co-authored 410 publications receiving 115921 citations. Previous affiliations of Ruslan Salakhutdinov include Carnegie Learning & University of Toronto.
Papers
More filters
Posted Content
Towards Understanding and Mitigating Social Biases in Language Models
TL;DR: This article proposed new benchmarks and metrics to measure the representational biases of LMs and proposed steps towards mitigating social biases during text generation, thereby pushing forward the performance-fairness Pareto frontier.
S calable and p rivacy - enhanced g raph g ener ative m odel for g raph n eural n etworks
TL;DR: This work introduces a novel graph generative model, Computation Graph Transformer (CGT), that can learn and reproduce the distribution of real-world graphs in a privacy-enhanced way and generates effective benchmark graphs on which GNNs show similar task performance as on the source graphs.
Journal ArticleDOI
Zero-shot Domain Adaptation of Heterogeneous Graphs via Knowledge Transfer Networks
TL;DR: This work theoretically induce a relationship between source and target domain features extracted from HGNNs, then proposes a novel domain adaptation method, Knowledge Transfer Networks for HGNNS (HGNN-KTN), which outperforms state-of-the-art baselines and outperforms MRR on 18 different domain adaptation tasks running on real-world benchmark graphs.
Posted Content
FILM: Following Instructions in Language with Modular Methods
TL;DR: The authors propose a modular method with structured representations that builds a semantic map of the scene, and performs exploration with a semantic search policy, to achieve the natural language goal, achieving state tracking, spatial memory, exploration, and long-term planning.
Posted Content
Understanding the Tradeoffs in Client-side Privacy for Downstream Speech Tasks
Peter Wu,Paul Pu Liang,Jiatong Shi,Ruslan Salakhutdinov,Shinji Watanabe,Louis-Philippe Morency +5 more
TL;DR: In this article, the authors formally define client-side privacy and discuss its three unique technical challenges: direct manipulation of raw data on client devices, adaptability with a broad range of server-side processing models, and low time and space complexity for compatibility with limited-bandwidth devices.