Search Results for author: Krzysztof Maziarz

Found 12 papers, 4 papers with code

Re-evaluating Retrosynthesis Algorithms with Syntheseus

1 code implementation30 Oct 2023 Krzysztof Maziarz, Austin Tripp, Guoqing Liu, Megan Stanley, Shufang Xie, Piotr Gaiński, Philipp Seidl, Marwin Segler

The planning of how to synthesize molecules, also known as retrosynthesis, has been a growing focus of the machine learning and chemistry communities in recent years.

Benchmarking Multi-step retrosynthesis +1

Retro-fallback: retrosynthetic planning in an uncertain world

no code implementations13 Oct 2023 Austin Tripp, Krzysztof Maziarz, Sarah Lewis, Marwin Segler, José Miguel Hernández-Lobato

Retrosynthesis is the task of proposing a series of chemical reactions to create a desired molecule from simpler, buyable molecules.

Retrosynthesis

Are VAEs Bad at Reconstructing Molecular Graphs?

no code implementations4 May 2023 Hagen Muenkler, Hubert Misztela, Michal Pikusa, Marwin Segler, Nadine Schneider, Krzysztof Maziarz

Many contemporary generative models of molecules are variational auto-encoders of molecular graphs.

Retrosynthetic Planning with Dual Value Networks

1 code implementation31 Jan 2023 Guoqing Liu, Di Xue, Shufang Xie, Yingce Xia, Austin Tripp, Krzysztof Maziarz, Marwin Segler, Tao Qin, Zongzhang Zhang, Tie-Yan Liu

Retrosynthesis, which aims to find a route to synthesize a target molecule from commercially available starting materials, is a critical task in drug discovery and materials design.

Drug Discovery Multi-step retrosynthesis +2

Holistic Multi-View Building Analysis in the Wild with Projection Pooling

no code implementations23 Aug 2020 Zbigniew Wojna, Krzysztof Maziarz, Łukasz Jocz, Robert Pałuba, Robert Kozikowski, Iasonas Kokkinos

To this end, we introduce a new benchmarking dataset, consisting of 49426 images (top-view and street-view) of 9674 buildings.

Benchmarking

Flexible Multi-task Networks by Learning Parameter Allocation

no code implementations10 Oct 2019 Krzysztof Maziarz, Efi Kokiopoulou, Andrea Gesmundo, Luciano Sbaiz, Gabor Bartok, Jesse Berent

The binary allocation variables are learned jointly with the model parameters by standard back-propagation thanks to the Gumbel-Softmax reparametrization method.

Multi-Task Learning

Evo-NAS: Evolutionary-Neural Hybrid Agent for Architecture Search

no code implementations25 Sep 2019 Krzysztof Maziarz, Mingxing Tan, Andrey Khorlin, Kuang-Yu Samuel Chang, Andrea Gesmundo

We show that the Evo-NAS agent outperforms both neural and evolutionary agents when applied to architecture search for a suite of text and image classification benchmarks.

Evolutionary Algorithms Image Classification +2

Gumbel-Matrix Routing for Flexible Multi-task Learning

no code implementations25 Sep 2019 Krzysztof Maziarz, Efi Kokiopoulou, Andrea Gesmundo, Luciano Sbaiz, Gabor Bartok, Jesse Berent

We propose the Gumbel-Matrix routing, a novel multi-task routing method based on the Gumbel-Softmax, that is designed to learn fine-grained parameter sharing.

Multi-Task Learning

Evolutionary-Neural Hybrid Agents for Architecture Search

no code implementations24 Nov 2018 Krzysztof Maziarz, Mingxing Tan, Andrey Khorlin, Marin Georgiev, Andrea Gesmundo

We show that the Evo-NAS agent outperforms both neural and evolutionary agents when applied to architecture search for a suite of text and image classification benchmarks.

Evolutionary Algorithms General Classification +3

Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer

4 code implementations23 Jan 2017 Noam Shazeer, Azalia Mirhoseini, Krzysztof Maziarz, Andy Davis, Quoc Le, Geoffrey Hinton, Jeff Dean

In this work, we address these challenges and finally realize the promise of conditional computation, achieving greater than 1000x improvements in model capacity with only minor losses in computational efficiency on modern GPU clusters.

Computational Efficiency Language Modelling +2

Cannot find the paper you are looking for? You can Submit a new open access paper.