Probabilistic Dependency Graphs

02/02/2021

Probabilistic Dependency Graphs

Oliver Richardson, Joseph Y Halpern

Keywords:

Abstract Paper Similar Papers

Abstract: We introduce Probabilistic Dependency Graphs (PDGs), a new class of directed graphical models. PDGs can capture inconsistent beliefs in a natural way and are more modular than Bayesian Networks (BNs), in that they make it easier to incorporate new information and restructure the representation. We show by example how PDGs are an especially natural modeling tool. We provide three semantics for PDGs, each of which can be derived from a scoring function (on joint distributions over the variables in the network) that can be viewed as representing a distribution's incompatibility with the PDG. For the PDG corresponding to a BN, this function is uniquely minimized by the distribution the BN represents, showing that PDG semantics extend BN semantics. We show further that factor graphs and their exponential families can also be faithfully represented as PDGs, while there are significant barriers to modeling a PDG with a factor graph.

The video of this talk cannot be embedded. You can watch it here:

https://slideslive.com/38949067

(Link will open in new window)

0

0

0

0

Share

This is an embedded video. Talk and the respective paper are published at AAAI 2021 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment

no comments yet

Similar Papers

18/07/2021

Directional Graph Networks

Dominique Beaini, Saro Passaro, Vincent Létourneau and
Will Hamilton, Gabriele Corso, Pietro Lió

Keywords Paper

Deep Learning

0

0

0

0

17:04

03/05/2021

My Body is a Cage: the Role of Morphology in Graph-Based Incompatible Control

Vitaly Kurin, Maximilian Igl, Tim Rocktaeschel and
Wendelin Boehmer, Shimon Whiteson

Keywords Paper

Incompatible Environments, Continuous Control, Multitask Reinforcement Learning, Deep Reinforcement Learning, Graph Neural Networks

0

0

0

0

5:03

03/05/2021

Categorical Normalizing Flows via Continuous Transformations

Phillip Lippe, Stratis Gavves

Keywords Paper

Normalizing Flows, Graph Generation, Density Estimation

0

0

0

0

4:40

05/12/2020

AMR quality rating with a lightweight CNN

Juri Opitz

Keywords Paper

0

0

0

0

14:54

14/06/2020

Probabilistic Structural Latent Representation for Unsupervised Embedding

Mang Ye, Jianbing Shen

Keywords Paper

unsupervised embedding learning, latent representation, instance feature, adaptable softmax

0

0

0

0

0:59

25/07/2020

Disentangled graph collaborative filtering

Xiang Wang, Hongye Jin, An Zhang and
Xiangnan He, Tong Xu, Tat-Seng Chua

Keywords Paper

explainable recommendation, disentangled representation learning, collaborative filtering, graph neural networks

0

0

0

0

15:17

19/08/2021

Improved Acyclicity Reasoning for Bayesian Network Structure Learning with Constraint Programming

Fulya Trösser, Simon de Givry, George Katsirelos

Keywords Paper

Uncertainty in AI, Bayesian Networks, Constraint Optimization

0

0

0

0

12:32

18/07/2021

Weisfeiler and Lehman Go Topological: Message Passing Simplicial Networks

Cristian Bodnar, Fabrizio Frasca, Yu Guang Wang and
Nina Otter, Guido Montufar, Pietro Lió, Michael Bronstein

Keywords Paper

Algorithms, Networks and Relational Learning

0

0

0

0

5:13

06/12/2021

Diverse Message Passing for Attribute with Heterophily

Liang Yang, Mengzhe Li, Liyang Liu and
bingxin niu, Chuan Wang, Xiaochun Cao, Yuanfang Guo

Keywords Paper

deep learning, optimization, graph learning

0

0

0

0

12:59

19/08/2021

CogTree: Cognition Tree Loss for Unbiased Scene Graph Generation

Jing Yu, Yuan Chai, Yujing Wang and
Yue Hu, Qi Wu

Keywords Paper

Computer Vision, Language and Vision

0

0

0

0

15:08

06/12/2021

Robustifying Algorithms of Learning Latent Trees with Vector Variables

Fengzhuo Zhang, Vincent Tan

Keywords Paper

theory, graph learning

0

0

0

0

13:21

12/07/2020

Ordinal Non-negative Matrix Factorization for Recommendation

Olivier Gouvert, Thomas Oberlin, Cedric Fevotte

Keywords Paper

General Machine Learning Techniques

0

0

0

0

15:17

18/07/2021

Understanding self-supervised learning dynamics without contrastive pairs

Yuandong Tian, Xinlei Chen, Surya Ganguli

Keywords Paper

Deep Learning, Optimization for Deep Networks

0

0

0

0

18:16

08/12/2020

Bracketing Encodings for 2-Planar Dependency Parsing

Michalina Strzyz, David Vilares, Carlos Gómez-Rodríguez

Keywords Paper

0

0

0

0

11:42

02/02/2021

Why Do Attributes Propagate in Graph Convolutional Neural Networks?

Liang Yang, Chuan Wang, Junhua Gu and
Xiaochun Cao, Bingxin Niu

Keywords Paper

0

0

0

0

16:16

13/04/2021

Hyperbolic graph embedding with enhanced semi-implicit variational inference.

Ali Lotfi Rezaabad, Rahi Kalantari, Sriram Vishwanath and
Mingyuan Zhou, Jonathan Tamir

Keywords Paper

0

0

0

0

3:09

18/07/2021

Regularized Submodular Maximization at Scale

Ehsan Kazemi, shervin minaee, Moran Feldman, Amin Karbasi

Keywords Paper

Optimization, Combinatorial Optimization

0

0

0

0

5:17

16/11/2020

Lightweight, Dynamic Graph Convolutional Networks for AMR-to-Text Generation

Yan Zhang, Zhijiang Guo, Zhiyang Teng and
Wei Lu, Shay B. Cohen, Zuozhu Liu, Lidong Bing

Keywords Paper

amr-to-text generation, graph representations, graph gcns, gcns

0

0

0

0

11:22

12/07/2020

LowFER: Low-rank Bilinear Pooling for Link Prediction

Saadullah Amin, Stalin Varanasi, Katherine Ann Dunfield, Günter Neumann

Keywords Paper

Applications - Language, Speech and Dialog

0

0

0

0

14:36

14/06/2020

Continual Learning With Extended Kronecker-Factored Approximate Curvature

Janghyeon Lee, Hyeong Gwon Hong, Donggyu Joo, Junmo Kim

Keywords Paper

continual learning, curvature approximation, extended k-fac

0

0

0

0

1:01

23/08/2020

NodeAug: Semi-supervised node classification with data augmentation

Yiwei Wang, Wei Wang, Yuxuan Liang and
Yujun Cai, Juncheng Liu, Bryan Hooi

Keywords Paper

graph convolutional networks, data augmentation, semi-supervised learning, graph mining

0

0

0

0

11:29

02/02/2021

Efficient Bayesian Network Structure Learning via Parameterized Local Search on Topological Orderings

Niels Grüttemeier, Christian Komusiewicz, Nils Morawietz

Keywords Paper

0

0

0

0

15:52

19/10/2020

Denoising individual bias for fairer binary submatrix detection

Changlin Wan, Wennan Chang, Tong Zhao and
Sha Cao, Chi Zhang

Keywords Paper

binary data mining, denoising, fairness, low rank representation

0

0

0

0

6:23

06/12/2020

Active Structure Learning of Causal DAGs via Directed Clique Trees

Chandler Squires, Sara Magliacane, Kristjan Greenewald and
Dmitriy Katz, Murat Kocaoglu, Karthikeyan Shanmugam

Keywords Paper

0

0

0

0

3:23

06/12/2021

Low-Rank Subspaces in GANs

Jiapeng Zhu, Ruili Feng, Yujun Shen and
Deli Zhao, Zheng-Jun Zha, Jingren Zhou, Qifeng Chen

Keywords Paper

generative model

0

0

0

0

11:41

04/07/2020

pyBART: Evidence-based Syntactic Transformations for IE

Aryeh Tiktinsky, Yoav Goldberg, Reut Tsarfaty

Keywords Paper

IE, machine-learned tasks, downstream applications, data-driven transformations

0

0

0

0

14:02

23/08/2020

Scaling choice models of relational social data

Jan Overgoor, George Pakapol Supaniratisai, Johan Ugander

Keywords Paper

network formation, choice models, social networks

0

0

0

0

17:51

06/12/2020

Provable Online CP/PARAFAC Decomposition of a Structured Tensor via Dictionary Learning

Sirisha Rambhatla, Xingguo Li, Jarvis Haupt

Keywords Paper

0

0

0

0

3:22

06/12/2021

Capacity and Bias of Learned Geometric Embeddings for Directed Graphs

Michael Boratko, Dongxu Zhang, Nicholas Monath and
Luke Vilnis, Kenneth L Clarkson, Andrew McCallum

Keywords Paper

machine learning, graph learning, representation learning

0

0

0

0

14:56

01/07/2020

Span-Based LCFRS-2 Parsing

Miloš Stanojević, Mark Steedman

Keywords Paper

0

0

0

0

14:37

06/12/2021

Non-approximate Inference for Collective Graphical Models on Path Graphs via Discrete Difference of Convex Algorithm

Yasunori Akagi, Naoki Marumo, Hideaki Kim and
Takeshi Kurashima, Hiroyuki Toda

Keywords Paper

graph learning

0

0

0

0

11:13

22/11/2021

Adaptive Tensor Networks Decomposition

Chang Nie, Huan Wang, Le Tian

Keywords Paper

Tensor networks, Adaptive decomposition, Tensor completion, Neural network compression.

0

0

0

0

2:39

17/08/2020

MGCN: Descriptor learning using multiscale GCNs

Yiqun Wang, Jing Ren, Dong-Ming Yan and
Jianwei Guo, Xiaopeng Zhang, Peter Wonka

Keywords Paper

wavelet convolution, shape matching, multiscale, energy decomposition

0

0

0

0

17:36

19/10/2020

Robust normalized squares maximization for unsupervised domain adaptation

Wenju Zhang, Xiang Zhang, Qing Liao and
Wenjing Yang, Long Lan, Zhigang Luo

Keywords Paper

transfer learning, image classification, domain adaptation

0

0

0

0

6:23

02/02/2021

Interpreting Deep Neural Networks with Relative Sectional Propagation by Analyzing Comparative Gradients and Hostile Activations

Woo-Jeoung Nam, Jaesik Choi, Seong-Whan Lee

Keywords Paper

0

0

0

0

14:51

13/04/2021

Graphical normalizing flows

Antoine Wehenkel, Gilles Louppe

Keywords Paper

0

0

0

0

3:04

06/12/2021

Consistency Regularization for Variational Auto-Encoders

Samarth Sinha, Adji Bousso Dieng

Keywords Paper

deep learning, machine learning, self-supervised learning, generative model, contrastive learning, representation learning

0

0

0

0

10:52

06/12/2020

Digraph Inception Convolutional Networks

Zekun Tong, Yuxuan Liang, Changsheng Sun and
Xinke Li, David Rosenblum, Andrew Lim

Keywords Paper

0

0

0

0

3:22

06/12/2021

Differentiable Equilibrium Computation with Decision Diagrams for Stackelberg Models of Combinatorial Congestion Games

Shinsaku Sakaue, Kengo Nakamura

Keywords Paper

optimization

0

0

0

0

15:07

05/01/2021

Exploiting Spatial Relation for Reducing Distortion in Style Transfer

Jia-Ren Chang, Yong-Sheng Chen

Keywords Paper

0

0

0

0

4:54