Search Results for author:
Found 28 papers, 10 papers with code
Self-Supervised Pretraining for Heterogeneous Hypergraph Neural Networks
SPHH is consist of two self-supervised pretraining tasks that aim to simultaneously learn both local and global representations of the entities in the hypergraph by using informative representations derived from the hypergraph structure.
Learning on Random Balls is Sufficient for Estimating (Some) Graph Parameters
Theoretical analyses for graph learning methods often assume a complete observation of the input graph.
Abelian Neural Networks
We study the problem of modeling a binary operation that satisfies some algebraic requirements.
Adaptive Stacked Graph Filter
We study Graph Convolutional Networks (GCN) from the graph signal processing viewpoint by addressing a difference between learning graph filters with fully-connected weights versus trainable polynomial coefficients.
Stacked Graph Filter
We study Graph Convolutional Networks (GCN) from the graph signal processing viewpoint by addressing a difference between learning graph filters with fully connected weights versus trainable polynomial coefficients.
Graph Homomorphism Convolution
In this paper, we study the graph classification problem from the graph homomorphism perspective.
Tightly Robust Optimization via Empirical Domain Reduction
Data-driven decision-making is performed by solving a parameterized optimization problem, and the optimal decision is given by an optimal solution for unknown true parameters.
Learning Directly from Grammar Compressed Text
Neural networks using numerous text data have been successfully applied to a variety of tasks.
A Simple Proof of the Universality of Invariant/Equivariant Graph Neural Networks
We present a simple proof for the universality of invariant and equivariant tensorized graph neural networks.
Frequency Analysis for Graph Convolution Network
In this work, we develop quantitative results to the learnablity of a two-layers Graph Convolutional Network (GCN).
Empirical Hypothesis Space Reduction
Selecting appropriate regularization coefficients is critical to performance with respect to regularized empirical risk minimization problems.
Data Cleansing for Models Trained with SGD
Data cleansing is a typical approach used to improve the accuracy of machine learning models, which, however, requires extensive domain knowledge to identify the influential instances that affect the models.
Revisiting Graph Neural Networks: All We Have is Low-Pass Filters
However, we find that the feature vectors of benchmark datasets are already quite informative for the classification task, and the graph structure only provides a means to denoise the data.
Faking Fairness via Stealthily Biased Sampling
The focus of this study is to raise an awareness of the risk of malicious decision-makers who fake fairness by abusing the auditing tools and thereby deceiving the social communities.
Joint Learning of Hierarchical Word Embeddings from a Corpus and a Taxonomy
To learn the word embeddings, the proposed method considers not only the hypernym relations that exists between words on a taxonomy, but also their contextual information in a large text corpus.
Convex Hull Approximation of Nearly Optimal Lasso Solutions
To this end, we formulate the problem as finding a small number of solutions such that the convex hull of these solutions approximates the set of nearly optimal solutions.
A Simple Way to Deal with Cherry-picking
Statistical hypothesis testing serves as statistical evidence for scientific innovation.
Feature Attribution As Feature Selection
In this study, we formalize the feature attribution problem as a feature selection problem.
Maximally Invariant Data Perturbation as Explanation
In adversarial example, one seeks the smallest data perturbation that changes the model's output.
ClassiNet -- Predicting Missing Features for Short-Text Classification
We propose \emph{ClassiNet} -- a network of classifiers trained for predicting missing features in a given instance, to overcome the feature sparseness problem.
Neural Inverse Rendering for General Reflectance Photometric Stereo
We present a novel convolutional neural network architecture for photometric stereo (Woodham, 1980), a problem of recovering 3D object surface normals from multiple images observed under varying illuminations.
On Tensor Train Rank Minimization : Statistical Efficiency and Scalable Algorithm
Tensor train (TT) decomposition provides a space-efficient representation for higher-order tensors.
On Tensor Train Rank Minimization: Statistical Efficiency and Scalable Algorithm
Tensor train (TT) decomposition provides a space-efficient representation for higher-order tensors.
Finding Alternate Features in Lasso
We propose a method for finding alternate features missing in the Lasso optimal solution.
Joint Word Representation Learning using a Corpus and a Semantic Lexicon
For this purpose, we propose a joint word representation learning method that simultaneously predicts the co-occurrences of two words in a sentence subject to the relational constrains given by the semantic lexicon.
Unsupervised Cross-Domain Word Representation Learning
Given a pair of \emph{source}-\emph{target} domains, we propose an unsupervised method for learning domain-specific word representations that accurately capture the domain-specific aspects of word semantics.
Embedding Semantic Relations into Word Representations
We propose an unsupervised method for learning vector representations for words such that the learnt representations are sensitive to the semantic relations that exist between two words.
Learning Word Representations from Relational Graphs
To evaluate the accuracy of the word representations learnt using the proposed method, we use the learnt word representations to solve semantic word analogy problems.
