arXiv subjects

Zehao Dong

Publications and source records attributed to Zehao Dong.

22 records · Page 2Linked to original sources

arXiv2022

PACE: A Parallelizable Computation Encoder for Directed Acyclic Graphs

Optimization of directed acyclic graph (DAG) structures has many applications, such as neural architecture search (NAS) and probabilistic graphical model learning. Encoding DAGs into real vectors is a dominant component in most neural-network-based DAG optimization frameworks. Currently, most DAG encoders use an asynchronous message passing scheme which sequentially processes nodes according to the dependency between nodes in a DAG. That is, a node must not be processed until all its predecessors are processed. As a result, they are inherently not parallelizable. In this work, we propose a Parallelizable Attention-based Computation structure Encoder (PACE) that processes nodes simultaneously and encodes DAGs in parallel. We demonstrate the superiority of PACE through encoder-dependent optimization subroutines that search the optimal DAG structure based on the learned DAG embeddings. Experiments show that PACE not only improves the effectiveness over previous sequential DAG encoders with a significantly boosted training and inference speed, but also generates smooth latent (DAG encoding) spaces that are beneficial to downstream optimization subroutines. Our source code is available at \url{https://github.com/zehao-dong/PACE}

cs.LG↗

arXiv2022

Multi-state data storage in a two-dimensional stripy antiferromagnet implemented by magnetoelectric effect

A promising approach to the next generation of low-power, functional, and energy-efficient electronics relies on novel materials with coupled magnetic and electric degrees of freedom. In particular, stripy antiferromagnets often exhibit broken crystal and magnetic symmetries, which may bring about the magnetoelectric (ME) effect and enable the manipulation of intriguing properties and functionalities by electrical means. The demand for expanding the boundaries of data storage and processing technologies has led to the development of spintronics toward two-dimensional (2D) platforms. This work reports the ME effect in the 2D stripy antiferromagnetic insulator CrOCl down to a single layer. By measuring the tunneling resistance of CrOCl on the parameter space of temperature, magnetic field, and applied voltage, we verified the ME coupling down to the 2D limit and unraveled its mechanism. Utilizing the multi-stable states and ME coupling at magnetic phase transitions, we realize multi-state data storage in the tunneling devices. Our work not only advances the fundamental understanding of spin-charge coupling but also demonstrates the great potential of 2D antiferromagnetic materials to deliver devices and circuits beyond the traditional binary operations.

cond-mat.mtrl-sci↗

arXiv2022

TOI-3714 b and TOI-3629 b: Two gas giants transiting M dwarfs confirmed with HPF and NEID

We confirm the planetary nature of two gas giants discovered by TESS to transit M dwarfs. TOI-3714 ($V=15.24,~J=11.74$) is an M2 dwarf hosting a hot Jupiter ($M_p=0.70 \pm 0.03~\mathrm{M_J}$ and $R_p=1.01 \pm 0.03~\mathrm{R_J}$) on an orbital period of $2.154849 \pm 0.000001$ days with a resolved white dwarf companion. TOI-3629 ($V=14.63,~J=11.42$) is an M1 dwarf hosting a hot Jupiter ($M_p=0.26 \pm 0.02~\mathrm{M_J}$ and $R_p=0.74 \pm 0.02~\mathrm{R_J}$) on an orbital period of $3.936551_{-0.000006}^{+0.000005}$ days. We characterize each transiting companion using a combination of ground-based and space-based photometry, speckle imaging, and high-precision velocimetry from the Habitable-zone Planet Finder and the NEID spectrographs. With the discovery of these two systems, there are now nine M dwarfs known to host transiting hot Jupiters. Among this population, TOI-3714 b ($T_{eq}=750\pm20$ K and $\mathrm{TSM}=98\pm7$) and TOI-3629 b ($T_{eq}=690\pm20$ K and $\mathrm{TSM}=80\pm9$) are warm gas giants amenable to additional characterization with transmission spectroscopy to probe atmospheric chemistry and, for TOI-3714, obliquity measurements to probe formation scenarios.

astro-ph.EP↗

arXiv2021

Interpretable Drug Synergy Prediction with Graph Neural Networks for Human-AI Collaboration in Healthcare

We investigate molecular mechanisms of resistant or sensitive response of cancer drug combination therapies in an inductive and interpretable manner. Though deep learning algorithms are widely used in the drug synergy prediction problem, it is still an open problem to formulate the prediction model with biological meaning to investigate the mysterious mechanisms of synergy (MoS) for the human-AI collaboration in healthcare systems. To address the challenges, we propose a deep graph neural network, IDSP (Interpretable Deep Signaling Pathways), to incorporate the gene-gene as well as gene-drug regulatory relationships in synergic drug combination predictions. IDSP automatically learns weights of edges based on the gene and drug node relations, i.e., signaling interactions, by a multi-layer perceptron (MLP) and aggregates information in an inductive manner. The proposed architecture generates interpretable drug synergy prediction by detecting important signaling interactions, and can be implemented when the underlying molecular mechanism encounters unseen genes or signaling pathways. We test IDWSP on signaling networks formulated by genes from 46 core cancer signaling pathways and drug combinations from NCI ALMANAC drug combination screening data. The experimental results demonstrated that 1) IDSP can learn from the underlying molecular mechanism to make prediction without additional drug chemical information while achieving highly comparable performance with current state-of-art methods; 2) IDSP show superior generality and flexibility to implement the synergy prediction task on both transductive tasks and inductive tasks. 3) IDSP can generate interpretable results by detecting different salient signaling patterns (i.e. MoS) for different cell lines.

cs.LG↗