Tijin Yan

Ph.D. candidate in BIT

0%

NIPS 20 paperlist

Posted on Edited on In , Views: Valine:
Symbols count in article: 7.4k Reading time ≈ 7 mins.

NeuraIPS’20

Time Series

  • Probabilistic Time Series Forecasting with Shape and Temporal Diversity
  • Deep reconstruction of strange attractors from time series
  • Neural Controlled Differential Equations for Irregular Time Series
  • Adversarial Sparse Transformer for Time Series Forecasting
  • Learning Long-Term Dependencies in Irregularly-Sampled Time Series
  • Benchmarking Deep Learning Interpretability in Time Series Predictions
  • High-recall causal discovery for autocorrelated time series with latent confounders
  • Deep Rao-Blackwellised Particle Filters for Time Series Forecasting
  • Normalizing Kalman Filters for Multivariate Time Series Analysis
  • Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting
  • Learning Continuous System Dynamics from Irregularly-Sampled Partial Observations
  • Gamma-Models: Generative Temporal Difference Learning for Infinite-Horizon Prediction

GNN

  • Open Graph Benchmark: Datasets for Machine Learning on Graphs
  • Path Integral Based Convolution and Pooling for Graph Neural Networks
  • Stochastic Deep Gaussian Processes over Graphs
  • Scalable Graph Neural Networks via Bidirectional Propagation
  • Set2Graph: Learning Graphs From Sets
  • Multipole Graph Neural Operator for Parametric Partial Differential Equations
  • Parameterized Explainer for Graph Neural Network
  • Random Walk Graph Neural Networks
  • Dirichlet Graph Variational Autoencoder
  • Natural Graph Networks
  • Optimization and Generalization Analysis of Transduction through Gradient Boosting and Application to Multi-scale Graph Neural Networks
  • Weisfeiler and Leman go sparse: Towards scalable higher-order graph embeddings
  • Unsupervised Joint k-node Graph Representations with Compositional Energy-Based Models
  • PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks
  • Implicit Graph Neural Networks

  • Towards Deeper Graph Neural Networks with Differentiable Group Normalization

  • COPT: Coordinated Optimal Transport on Graphs

  • Less is More: A Deep Graph Metric Learning Perspective Using Few Proxies
  • Probabilistic Circuits for Variational Inference in Discrete Graphical Models
  • Deep Relational Topic Modeling via Graph Poisson Gamma Belief Network
  • Graph Stochastic Neural Networks for Semi-supervised Learning
  • Community detection in sparse time-evolving graphs with a dynamical Bethe-Hessian
  • Graph Random Neural Networks for Semi-Supervised Learning on Graphs
  • Learning of Discrete Graphical Models with Neural Networks
  • Building powerful and equivariant graph neural networks with message-passing
  • Manifold structure in graph embeddings

  • Attribution for Graph Neural Networks

  • Factorizable Graph Convolutional Networks

  • Handling Missing Data with Graph Representation Learning

  • EvolveGraph: Multi-Agent Trajectory Prediction with Dynamic Relational Reasoning

  • Design Space for Graph Neural Networks

  • Pointer Graph Networks
  • Reward Propagation Using Graph Convolutional Networks
  • Subgraph Neural Networks

  • Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs

  • Efficient Learning of Discrete Graphical Models

  • Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting
  • Learning to Execute Programs with Instruction Pointer Attention Graph Neural Networks
  • Scattering GCN: Overcoming Oversmoothness in Graph Convolutional Networks
  • Pre-Training Graph Neural Networks: A Contrastive Learning Framework with Augmentations
  • Variational Inference for Graph Convolutional Networks in the Absence of Graph Data and Adversarial Settings
  • A Novel Approach for Constrained Optimization in Graphical Models
  • Adversarially-learned Inference via an Ensemble of Discrete Undirected Graphical Models
  • Nonconvex Sparse Graph Learning under Laplacian-structured Graphical Model
  • Graph Geometry Interaction Learning
  • Bandit Samplers for Training Graph Neural Networks
  • Factor Graph Neural Networks
  • DiffGCN: Graph Convolutional Networks via Differential Operators and Algebraic Multigrid Pooling
  • Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting
  • Curvature Regularization to Prevent Distortion in Graph Embedding
  • Generalized Independent Noise Condition for Estimating Linear Non-Gaussian Latent Variable Graphs
  • Higher-Order Spectral Clustering of Directed Graphs
  • Iterative Deep Graph Learning for Graph NeuralNetworks: Better and Robust Node Embeddings
  • Graph Information Bottleneck
  • Rethinking pooling in graph neural networks

连续+Flow

  • Modeling Continuous Stochastic Processes with Dynamic Normalizing Flows
  • Inverse Rational Control with Partially Observable Continuous Nonlinear Dynamics
  • Riemannian Continuous Normalizing Flows
  • Continual Deep Learning by Functional Regularisation of Memorable Past
  • Scalable and Consistent Estimation in Continuous-time Networks of Relational Events
  • DAGs with No Fears: A Closer Look at Continuous Optimization for Learning Bayesian Networks
  • Hypersolvers: Toward Fast Continuous-Depth Models
  • Learning Continuous System Dynamics from Irregularly-Sampled Partial Observations
  • A mathematical model for automatic differentiation in machine learning
  • Neural Manifold Ordinary Differential Equations
  • Multipole Graph Neural Operator for Parametric Partial Differential Equations
  • Learning Differential Equations that are Fast to Solve
  • Interpolation technique to speed up gradients propagation in Neural Ordinary Differential Equations
  • JAX MD: A Framework for Differentiable Physics
  • Training Generative Adversarial Networks by Solving Ordinary Differential Equations
  • Numerically Solving Parametric Families of High-Dimensional Kolmogorov Partial Differential Equations via Deep Learning
  • Improved Variational Bayesian Phylogenetic Inference with Normalizing Flows
  • Flows for simultaneous manifold learning and density estimation
  • Wavelet Flow: Fast Training of High Resolution Normalizing Flows
  • Advances in Black-Box VI: Normalizing Flows, Importance Weighting, and Optimization
  • Woodbury Transformations for Deep Generative Flows
  • SoftFlow: Probabilistic Framework for Normalizing Flow on Manifolds

  • Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search

  • The Convolution Exponential and Generalized Sylvester Flows

  • NanoFlow: scalable normalizing flows with sublinear parameter complexity
  • Training Normalizing Flows with the Information Bottleneck for Competitive Generative Classification
  • Log-Likelihood Ratio Minimizing Flows: Towards Robust and Quantifiable Neural Distribution Alignment
  • Why Normalizing Flows Fail to Detect Out-of-Distribution Data
  • Stochastic Normalizing Flows
  • SurVAE Flows: Surjections to Bridge the Gap between VAEs and Flows
  • Closing the Dequantization Gap: PixelCNN as a Single-Layer Flow
  • SVGD as a kernelized gradient flow of the chi-squared divergence
  • Gradient Boosted Normalizing Flows

ICLR2021投稿

ODE + Flow + Dyna

TS

GNN

MPC