Optimizing Graph Transformer Networks with Graph-based Techniques

no code implementations • 16 Jun 2021 • Loc Hoang, Udit Agarwal, Gurbinder Gill, Roshan Dathathri, Abhik Seal, Brian Martin, Keshav Pingali

Unfortunately, the space overhead of this approach can be large, so in practice it is used only for small graphs.

EVA: An Encrypted Vector Arithmetic Language and Compiler for Efficient Homomorphic Computation

4 code implementations • 27 Dec 2019 • Roshan Dathathri, Blagovesta Kostova, Olli Saarikivi, Wei Dai, Kim Laine, Madanlal Musuvathi

We believe that EVA would enable a wider adoption of FHE by making it easier to develop FHE applications and domain-specific FHE compilers.

Distributed Training of Embeddings using Graph Analytics

no code implementations • 8 Sep 2019 • Gurbinder Gill, Roshan Dathathri, Saeed Maleki, Madan Musuvathi, Todd Mytkowicz, Olli Saarikivi

This paper presents a distributed training framework for a class of applications that use Skip-gram-like models to generate embeddings.

Graph Generation Word Embeddings

CHET: Compiler and Runtime for Homomorphic Evaluation of Tensor Programs

no code implementations • 1 Oct 2018 • Roshan Dathathri, Olli Saarikivi, Hao Chen, Kim Laine, Kristin Lauter, Saeed Maleki, Madanlal Musuvathi, Todd Mytkowicz

Just as the hardware ISA interface enabled hardware advances to proceed independent of software advances in the compiler and language runtimes, HISA decouples compiler optimizations and runtimes for supporting FHE applications from advancements in the underlying FHE schemes.