Search Results for author:
Found 60 papers, 28 papers with code
{\mathcal{P}^2}: A Plan-and-Pretrain Approach for Knowledge Graph-to-Text Generation
Text verbalization of knowledge graphs is an important problem with wide application to natural language generation (NLG) systems.
BloomGML: Graph Machine Learning through the Lens of Bilevel Optimization
These optimal features typically depend on tunable parameters of the lower-level energy in such a way that the entire bilevel pipeline can be trained end-to-end.
GFS: Graph-based Feature Synthesis for Prediction over Relational Databases
Consequently, the prevalent approach for training machine learning models on data stored in relational databases involves performing feature engineering to merge the data from multiple tables into a single table and subsequently applying single table models.
MuseGNN: Interpretable and Convergent Graph Neural Network Layers at Scale
Among the many variants of graph neural network (GNN) architectures capable of modeling data with cross-instance relations, an important subclass involves layers designed such that the forward pass iteratively reduces a graph-regularized energy function of interest.
Efficient Link Prediction via GNN Layers Induced by Negative Sampling
Graph neural networks (GNNs) for link prediction can loosely be divided into two broad categories.
Robust Angular Synchronization via Directed Graph Neural Networks
The angular synchronization problem aims to accurately estimate (up to a constant additive phase) a set of unknown angles $\theta_1, \dots, \theta_n\in[0, 2\pi)$ from $m$ noisy measurements of their offsets $\theta_i-\theta_j \;\mbox{mod} \; 2\pi.$ Applications include, for example, sensor network localization, phase retrieval, and distributed clock synchronization.
How Graph Neural Networks Learn: Lessons from Training Dynamics
A long-standing goal in deep learning has been to characterize the learning behavior of black-box models in a more interpretable manner.
From Hypergraph Energy Functions to Hypergraph Neural Networks
Hypergraphs are a powerful abstraction for representing higher-order interactions between entities of interest.
NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification
In this paper, we introduce a novel all-pair message passing scheme for efficiently propagating node signals between arbitrary nodes, as an important building block for a pioneering Transformer-style network for node classification on large graphs, dubbed as \textsc{NodeFormer}.
Learning Manifold Dimensions with Conditional Variational Autoencoders
Although the variational autoencoder (VAE) and its conditional extension (CVAE) are capable of state-of-the-art results across multiple domains, their precise behavior is still not fully understood, particularly in the context of data (like images) that lie on or near a low-dimensional manifold.
DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusion
Real-world data generation often involves complex inter-dependencies among instances, violating the IID-data hypothesis of standard learning paradigms and posing a challenge for uncovering the geometric structures for learning desired instance representations.
FreshGNN: Reducing Memory Access via Stable Historical Embeddings for Graph Neural Network Training
A key performance bottleneck when training graph neural network (GNN) models on large, real-world graphs is loading node features onto a GPU.
Refined Edge Usage of Graph Neural Networks for Edge Prediction
However, existing methods lack elaborate design regarding the distinctions between two tasks that have been frequently overlooked: (i) edges only constitute the topology in the node classification task but can be used as both the topology and the supervisions (i. e., labels) in the edge prediction task; (ii) the node classification makes prediction over each individual node, while the edge prediction is determinated by each pair of nodes.
Self-supervised Amodal Video Object Segmentation
The key intuition is that the occluded part of an object can be explained away if that part is visible in other frames, possibly deformed as long as the deformation can be reasonably learned.
Descent Steps of a Relation-Aware Energy Produce Heterogeneous Graph Neural Networks
Moreover, the complexity of this trade-off is compounded in the heterogeneous graph case due to the disparate heterophily relationships between nodes of different types.
A Robust Stacking Framework for Training Deep Graph Models with Multifaceted Node Features
Graph Neural Networks (GNNs) with numerical node features and graph structure as inputs have demonstrated superior performance on various supervised learning tasks with graph data.
Learning Enhanced Representations for Tabular Data via Neighborhood Propagation
Prediction over tabular data is an essential and fundamental problem in many important downstream tasks.
Transformers from an Optimization Perspective
Deep learning models such as the Transformer are often constructed by heuristics and experience.
Handling Distribution Shifts on Graphs: An Invariance Perspective
There is increasing evidence suggesting neural networks' sensitivity to distribution shifts, so that research on out-of-distribution (OOD) generalization comes into the spotlight.
GNNRank: Learning Global Rankings from Pairwise Comparisons via Directed Graph Neural Networks
In this paper, we introduce neural networks into the ranking recovery problem by proposing the so-called GNNRank, a trainable GNN-based framework with digraph embedding.
On the Value of Infinite Gradients in Variational Autoencoder Models
A number of recent studies of continuous variational autoencoder (VAE) models have noted, either directly or indirectly, the tendency of various parameter gradients to drift towards infinity during training.
GRIN: Generative Relation and Intention Network for Multi-agent Trajectory Prediction
Learning the distribution of future trajectories conditioned on the past is a crucial problem for understanding multi-agent systems.
Implicit vs Unfolded Graph Neural Networks
It has been observed that graph neural networks (GNN) sometimes struggle to maintain a healthy balance between the efficient modeling long-range dependencies across nodes while avoiding unintended consequences such oversmoothed node representations or sensitivity to spurious edges.
Does your graph need a confidence boost? Convergent boosted smoothing on graphs with tabular node features
For supervised learning with tabular data, decision tree ensembles produced via boosting techniques generally dominate real-world applications involving iid training/test sets.
Why Propagate Alone? Parallel Use of Labels and Features on Graphs
In this regard, it has recently been proposed to use a randomly-selected portion of the training labels as GNN inputs, concatenated with the original node features for making predictions on the remaining labels.
Inductive Relation Prediction Using Analogy Subgraph Embeddings
Prevailing methods for relation prediction in heterogeneous graphs aim at learning latent representations (i. e., embeddings) of observed nodes and relations, and thus are limited to the transductive setting where the relation types must be known during training.
A Closer Look at Distribution Shifts and Out-of-Distribution Generalization on Graphs
We observe that in most cases, we need both a suitable domain generalization algorithm and a strong GNN backbone model to optimize out-of-distribution test performance.
Convergent Boosted Smoothing for Modeling GraphData with Tabular Node Features
Many practical modeling tasks require making predictions using tabular data composed of heterogeneous feature types (e. g., text-based, categorical, continuous, etc.).
ESCo: Towards Provably Effective and Scalable Contrastive Representation Learning
In this paper, we propose ESCo (Effective and Scalable Contrastive), a new contrastive framework which is essentially an instantiation of the Information Bottleneck principle under self-supervised learning settings.
Learning Hierarchical Graph Neural Networks for Image Clustering
Our hierarchical GNN uses a novel approach to merge connected components predicted at each level of the hierarchy to form a new graph at the next level.
From Canonical Correlation Analysis to Self-supervised Graph Neural Networks
We introduce a conceptually simple yet effective model for self-supervised representation learning with graph data.
Sparse Multi-Path Corrections in Fringe Projection Profilometry
Three-dimensional scanning by means of structured light illumination is an active imaging technique involving projecting and capturing a series of striped patterns and then using the observed warping of stripes to reconstruct the target object's surface through triangulating each pixel in the camera to a unique projector coordinate corresponding to a particular feature in the projected patterns.
Bag of Tricks for Node Classification with Graph Neural Networks
Over the past few years, graph neural networks (GNN) and label propagation-based methods have made significant progress in addressing node classification tasks on graphs.
Ranked #1 on
Node Property Prediction
on ogbn-proteins
Graph Neural Networks Inspired by Classical Iterative Algorithms
Despite the recent success of graph neural networks (GNN), common architectures often exhibit significant limitations, including sensitivity to oversmoothing, long-range dependencies, and spurious edges, e. g., as can occur as a result of graph heterophily or adversarial attacks.
A Biased Graph Neural Network Sampler with Near-Optimal Regret
Graph neural networks (GNN) have recently emerged as a vehicle for applying deep network architectures to graph and relational data.
Regioned Episodic Reinforcement Learning
Goal-oriented reinforcement learning algorithms are often good at exploration, not exploitation, while episodic algorithms excel at exploitation, not exploration.
Explore with Dynamic Map: Graph Structured Reinforcement Learning
In reinforcement learning, a map with states and transitions built based on historical trajectories is often helpful in exploration and exploitation.
Fork or Fail: Cycle-Consistent Training with Many-to-One Mappings
Cycle-consistent training is widely used for jointly learning a forward and inverse mapping between two domains of interest without the cumbersome requirement of collecting matched pairs within each domain.
Further Analysis of Outlier Detection with Deep Generative Models
The recent, counter-intuitive discovery that deep generative models (DGMs) can frequently assign a higher likelihood to outliers has implications for both outlier detection applications as well as our overall understanding of generative modeling.
CycleGT: Unsupervised Graph-to-Text and Text-to-Graph Generation via Cycle Training
Due to the difficulty and high cost of data collection, the supervised data available in the two fields are usually on the magnitude of tens of thousands, for example, 18K in the WebNLG~2017 dataset after preprocessing, which is far fewer than the millions of data for other tasks such as machine translation.
The Usual Suspects? Reassessing Blame for VAE Posterior Collapse
In narrow asymptotic settings Gaussian VAE models of continuous data have been shown to possess global optima aligned with ground-truth distributions.
Single Image Reflection Removal Exploiting Misaligned Training Data and Network Enhancements
Removing undesirable reflections from a single image captured through a glass window is of practical importance to visual computing systems.
Ranked #2 on
Reflection Removal
on SIR^2(Objects)
Diagnosing and Enhancing VAE Models
Although variational autoencoders (VAEs) represent a widely influential deep generative model, many aspects of the underlying energy function remain poorly understood.
Image Smoothing via Unsupervised Learning
Image smoothing represents a fundamental component of many disparate computer vision and graphics applications.
Compressing Neural Networks using the Variational Information Bottelneck
Neural networks can be compressed to reduce memory and computational requirements, or to increase accuracy by facilitating the use of a larger base architecture.
Compressing Neural Networks using the Variational Information Bottleneck
Neural networks can be compressed to reduce memory and computational requirements, or to increase accuracy by facilitating the use of a larger base architecture.
A Generic Deep Architecture for Single Image Reflection Removal and Image Smoothing
This paper proposes a deep neural network structure that exploits edge information in addressing representative low-level vision tasks such as layer separation and image filtering.
Hidden Talents of the Variational Autoencoder
Variational autoencoders (VAE) represent a popular, flexible form of deep generative model that can be stochastically fit to samples from a given random process using an information-theoretic variational bound on the true underlying distribution.
From Bayesian Sparsity to Gated Recurrent Nets
The iterations of many first-order algorithms, when applied to minimizing common regularized regression functions, often resemble neural network layers with pre-specified weights.
Revisiting Deep Intrinsic Image Decompositions
While invaluable for many computer vision applications, decomposing a natural image into intrinsic reflectance and shading layers represents a challenging, underdetermined inverse problem.
A Pseudo-Bayesian Algorithm for Robust PCA
Commonly used in many applications, robust PCA represents an algorithmic attempt to reduce the sensitivity of classical PCA to outliers.
Maximal Sparsity with Deep Networks?
The iterations of many sparse estimation algorithms are comprised of a fixed linear filter cascaded with a thresholding nonlinearity, which collectively resemble a typical neural network layer.
Pseudo-Bayesian Robust PCA: Algorithms and Analyses
Commonly used in computer vision and other applications, robust PCA represents an algorithmic attempt to reduce the sensitivity of classical PCA to outliers.
Unsupervised Extraction of Video Highlights Via Robust Recurrent Auto-encoders
With the growing popularity of short-form video sharing platforms such as \em{Instagram} and \em{Vine}, there has been an increasing need for techniques that automatically extract highlights from video.
Non-Convex Rank Minimization via an Empirical Bayesian Approach
In many applications that require matrix solutions of minimal rank, the underlying cost function is non-convex leading to an intractable, NP-hard optimization problem.
Exploring Algorithmic Limits of Matrix Rank Minimization under Affine Constraints
While elegant theoretical conditions elucidate when this replacement is likely to be successful, they are highly restrictive and convex algorithms fail when the ambient rank is too high or when the constraint set is poorly structured.
Non-Uniform Camera Shake Removal Using a Spatially-Adaptive Sparse Penalty
Typical blur from camera shake often deviates from the standard uniform convolutional assumption, in part because of problematic rotations which create greater blurring away from some unknown center point.
Non-Uniform Blind Deblurring with a Spatially-Adaptive Sparse Prior
Typical blur from camera shake often deviates from the standard uniform convolutional script, in part because of problematic rotations which create greater blurring away from some unknown center point.
Multi-image Blind Deblurring Using a Coupled Adaptive Sparse Prior
This paper presents a robust algorithm for estimating a single latent sharp image given multiple blurry and/or noisy observations.
Revisiting Bayesian Blind Deconvolution
Blind deconvolution involves the estimation of a sharp signal or image given only a blurry observation.
