Search Results for author:
Found 20 papers, 15 papers with code
Descriptive Kernel Convolution Network with Improved Random Walk Kernel
In this paper, we first revisit the RWK and its current usage in KCNs, revealing several shortcomings of the existing designs, and propose an improved graph kernel RWK+, by introducing color-matching random walks and deriving its efficient computation.
Pard: Permutation-Invariant Autoregressive Diffusion for Graph Generation
Current graph diffusion models generate graphs in a one-shot fashion, but they require extra features and thousands of denoising steps to achieve optimal performance.
Improving and Unifying Discrete&Continuous-time Discrete Denoising Diffusion
Discrete diffusion models have seen a surge of attention with applications on naturally discrete data such as language and graphs.
ADAMM: Anomaly Detection of Attributed Multi-graphs with Metadata: A Unified Neural Network Approach
Given a complex graph database of node- and edge-attributed multi-graphs as well as associated metadata for each graph, how can we spot the anomalous instances?
DSV: An Alignment Validation Loss for Self-supervised Outlier Model Selection
DSV captures the alignment between an augmentation function and the anomaly-generating mechanism with surrogate losses, which approximate the discordance and separability of test data, respectively.
End-to-End Augmentation Hyperparameter Tuning for Self-Supervised Anomaly Detection
The first is a new unsupervised validation loss that quantifies the alignment between the augmented training data and the (unlabeled) test data.
Graph Anomaly Detection with Unsupervised GNNs
This work aims to fill two gaps in the literature: We (1) design GLAM, an end-to-end graph-level anomaly detection model based on GNNs, and (2) focus on unsupervised model selection, which is notoriously hard due to lack of any labels, yet especially critical for deep NN based models with a long list of hyper-parameters.
A Practical, Progressively-Expressive GNN
Our model is practical and progressively-expressive, increasing in power with k and c. We demonstrate effectiveness on several benchmark datasets, achieving several state-of-the-art results with runtime and memory usage applicable to practical graphs.
Hyperparameter Sensitivity in Deep Outlier Detection: Analysis and a Scalable Hyper-Ensemble Solution
Outlier detection (OD) literature exhibits numerous algorithms as it applies to diverse domains.
Sign and Basis Invariant Networks for Spectral Graph Representation Learning
We introduce SignNet and BasisNet -- new neural architectures that are invariant to two key symmetries displayed by eigenvectors: (i) sign flips, since if $v$ is an eigenvector then so is $-v$; and (ii) more general basis symmetries, which occur in higher dimensional eigenspaces with infinitely many choices of basis eigenvectors.
Ranked #10 on
Graph Regression
on ZINC-500k
Graph Condensation for Graph Neural Networks
Given the prevalence of large-scale graphs in real-world applications, the storage and time for training neural models have raised increasing concerns.
Fast Attributed Graph Embedding via Density of States
We propose A-DOGE, for Attributed DOS-based Graph Embedding, based on density of states (DOS, a. k. a.
From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awareness
We choose the subgraph encoder to be a GNN (mainly MPNNs, considering scalability) to design a general framework that serves as a wrapper to up-lift any GNN.
Ranked #16 on
Graph Property Prediction
on ogbg-molpcba
Connecting Graph Convolution and Graph PCA
Based on this connection, the GCN architecture, shaped by stacking graph convolution layers, shares a close relationship with stacking GPCA.
On Using Classification Datasets to Evaluate Graph-Level Outlier Detection: Peculiar Observations and New Insights
We carefully study the graph embedding space produced by propagation based models and find two driving factors: (1) disparity between within-class densities which is amplified by propagation, and (2)overlapping support (mixing of embeddings) across classes.
Connecting Graph Convolutional Networks and Graph-Regularized PCA
Based on this connection, GCN architecture, shaped by stacking graph convolution layers, shares a close relationship with stacking GPCA.
Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs
We investigate the representation power of graph neural networks in the semi-supervised node classification task under heterophily or low homophily, i. e., in networks where connected nodes may have different class labels and dissimilar features.
Graph Unrolling Networks: Interpretable Neural Networks for Graph Signal Denoising
We unroll an iterative denoising algorithm by mapping each iteration into a single network layer where the feed-forward process is equivalent to iteratively denoising graph signals.
PairNorm: Tackling Oversmoothing in GNNs
The performance of graph neural nets (GNNs) is known to gradually decrease with increasing number of layers.
A Quest for Structure: Jointly Learning the Graph Structure and Semi-Supervised Classification
As such, PG-learn is a carefully-designed hybrid of random and adaptive search.
