paper-with-me

Papers

D-VAE: A Variational Autoencoder for Directed Acyclic Graphs

2019-04-24 · NeurIPS 2019 12 · Muhan Zhang, Shali Jiang, Zhicheng Cui, Roman Garnett, Yixin Chen

Graph structured data are abundant in the real world. Among different graph types, directed acyclic graphs (DAGs) are of particular interest to machine learning researchers, as many machine learning models are realized as computations on DAGs, including neural networks and Bayesian networks. In this paper, we study deep generative models for DAGs, and propose a novel DAG variational autoencoder (D-VAE). To encode DAGs into the latent space, we leverage graph neural networks. We propose an asynchronous message passing scheme that allows encoding the computations on DAGs, rather than using existing simultaneous message passing schemes to encode local graph structures. We demonstrate the effectiveness of our proposed DVAE through two tasks: neural architecture search and Bayesian network structure learning. Experiments show that our model not only generates novel and valid DAGs, but also produces a smooth latent space that facilitates searching for DAGs with better performance through Bayesian optimization.

📄 PDF Abstract BibTeX arXiv:1904.11088

Code (2)

muhanzhang/D-VAE 공식 구현 pytorch
muhanzhang/DVAE 공식 구현 pytorch

Tasks

Bayesian OptimizationBIG-bench Machine LearningNeural Architecture Searchvalid

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
Solana Customer Service Number +1-833-534-1729 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Similar Papers 제목 키워드 기반

ProDAG: Projected Variational Inference for Directed Acyclic Graphs

2024-05-24 · Ryan Thompson, Edwin V. Bonilla, Robert Kohn

Directed acyclic graph (DAG) learning is a central task in structure discovery and causal inference. Although the field has witnessed remarkable advances over the past few years, it remains statistically and computationa…

Causal InferenceCombinatorial OptimizationUncertainty Quantificationvalid+1

Scalable Variational Causal Discovery Unconstrained by Acyclicity

2024-07-06 · Nu Hoang, Bao Duong, Thin Nguyen

Bayesian causal discovery offers the power to quantify epistemic uncertainties among a broad range of structurally diverse causal theories potentially explaining the data, represented in forms of directed acyclic graphs …

Causal DiscoveryvalidVariational Inference

DAGSurv: Directed Acyclic Graph Based Survival Analysis Using Deep Neural Networks

2021-11-02 · Ansh Kumar Sharma, Rahul Kukreja, Ranjitha Prasad, Shilpa Rao

Causal structures for observational survival data provide crucial information regarding the relationships between covariates and time-to-event. We derive motivation from the information theoretic source coding argument, …

Survival AnalysisSurvival PredictionVariational Inference

Gravity-Inspired Graph Autoencoders for Directed Link Prediction

2019-05-23 · Guillaume Salha, Stratis Limnios, Romain Hennequin, Viet Anh Tran 외

Graph autoencoders (AE) and variational autoencoders (VAE) recently emerged as powerful node embedding methods. In particular, graph AE and VAE were successfully leveraged to tackle the challenging link prediction proble…

DecoderLink PredictionPrediction

Latent Optimal Paths by Gumbel Propagation for Variational Bayesian Dynamic Programming

2023-06-05 · Xinlei Niu, Christian Walder, Jing Zhang, Charles Patrick Martin

We propose the stochastic optimal path which solves the classical optimal path problem by a probability-softening solution. This unified approach transforms a wide range of DP problems into directed acyclic graphs in whi…

Bayesian InferenceSinging Voice Synthesistext-to-speechText to Speech