Search Results for author:
Found 42 papers, 19 papers with code
Towards reliable respiratory disease diagnosis based on cough sounds and vision transformers
Based on the observations from such an extensive empirical study, we propose a novel approach to cough-based disease classification based on both self-supervised and supervised learning on a large-scale cough data set.
You Can't Ignore Either: Unifying Structure and Feature Denoising for Robust Graph Learning
However, the noises and attacks may come from both structures and features in graphs, making the graph denoising a dilemma and challenging problem.
Foundations and Frontiers of Graph Learning Theory
Recent advancements in graph learning have revolutionized the way to understand and analyze data with complex structures.
SEFraud: Graph-based Self-Explainable Fraud Detection via Interpretative Mask Learning
While considerable efforts have been devoted to designing adequate fraud detectors, the interpretability of their results has often been overlooked.
Investigating Memory Failure Prediction Across CPU Architectures
Large-scale datacenters often experience memory failures, where Uncorrectable Errors (UEs) highlight critical malfunction in Dual Inline Memory Modules (DIMMs).
Enhancing Prompt Following with Visual Control Through Training-Free Mask-Guided Diffusion
Meanwhile, a network, dubbed as Masked ControlNet, is designed to utilize these object masks for object generation in the misaligned visual control region.
RHanDS: Refining Malformed Hands for Generated Images with Decoupled Structure and Style Guidance
The style guidance is a hand image, e. g., the malformed hand itself, and is employed to furnish the style reference for hand refining.
MATA*: Combining Learnable Node Matching with A* Algorithm for Approximate Graph Edit Distance Computation
Graph Edit Distance (GED) is a general and domain-agnostic metric to measure graph similarity, widely used in graph search or retrieving tasks.
Mitigating Semantic Confusion from Hostile Neighborhood for Graph Active Learning
Graph Active Learning (GAL), which aims to find the most informative nodes in graphs for annotation to maximize the Graph Neural Networks (GNNs) performance, has attracted many research efforts but remains non-trivial challenges.
TextPainter: Multimodal Text Image Generation with Visual-harmony and Text-comprehension for Poster Design
Specifically, TextPainter takes the global-local background image as a hint of style and guides the text image generation with visual harmony.
AutoPoster: A Highly Automatic and Content-aware Design System for Advertising Poster Generation
Meanwhile, to our knowledge, we propose the first poster generation dataset that includes visual attribute annotations for over 76k posters.
Hyperbolic Representation Learning: Revisiting and Advancing
To address this, we propose a simple yet effective method, hyperbolic informed embedding (HIE), by incorporating cost-free hierarchical information deduced from the hyperbolic distance of the node to origin (i. e., induced hyperbolic norm) to advance existing \hlms.
Unsupervised Domain Adaption with Pixel-level Discriminator for Image-aware Layout Generation
This paper focuses on using the GAN-based model conditioned on image contents to generate advertising poster graphic layouts, which requires an advertising poster layout dataset with paired product images and graphic layouts.
CF-Font: Content Fusion for Few-shot Font Generation
Content and style disentanglement is an effective way to achieve few-shot font generation.
UNREAL:Unlabeled Nodes Retrieval and Labeling for Heavily-imbalanced Node Classification
To select which unlabeled nodes to add, we propose geometric ranking to rank unlabeled nodes.
Traffic4cast at NeurIPS 2022 -- Predict Dynamics along Graph Edges from Sparse Node Data: Whole City Traffic and ETA from Stationary Vehicle Detectors
We only provide vehicle count data from spatially sparse stationary vehicle detectors in these three cities as model input for this task.
xASTNN: Improved Code Representations for Industrial Practice
The proposed xASTNN has three advantages.
kHGCN: Tree-likeness Modeling via Continuous and Discrete Curvature Learning
The prevalence of tree-like structures, encompassing hierarchical structures and power law distributions, exists extensively in real-world applications, including recommendation systems, ecosystems, financial networks, social networks, etc.
Resisting Graph Adversarial Attack via Cooperative Homophilous Augmentation
Recent studies show that Graph Neural Networks(GNNs) are vulnerable and easily fooled by small perturbations, which has raised considerable concerns for adapting GNNs in various safety-critical applications.
Deep Explainable Learning with Graph Based Data Assessing and Rule Reasoning
Learning an explainable classifier often results in low accuracy model or ends up with a huge rule set, while learning a deep model is usually more capable of handling noisy data at scale, but with the cost of hard to explain the result and weak at generalization.
Hyperbolic Graph Representation Learning: A Tutorial
We first give a brief introduction to graph representation learning as well as some preliminary Riemannian and hyperbolic geometry.
Transposed Variational Auto-encoder with Intrinsic Feature Learning for Traffic Forecasting
In this technical report, we present our solutions to the Traffic4cast 2022 core challenge and extended challenge.
Geometry Aligned Variational Transformer for Image-conditioned Layout Generation
First, self-attention mechanism is adopted to model the contextual relationship within layout elements, while cross-attention mechanism is used to fuse the visual information of conditional images.
Towards Learning in Grey Spatiotemporal Systems: A Prophet to Non-consecutive Spatiotemporal Dynamics
To infer region-wise proximity under flexible factor-wise combinations and enable dynamic neighborhood aggregations, we further disentangle compounded influences of exogenous factors on region-wise proximity and learn to aggregate them.
HICF: Hyperbolic Informative Collaborative Filtering
The results reveal that (1) tail items get more emphasis in hyperbolic space than that in Euclidean space, but there is still ample room for improvement; (2) head items receive modest attention in hyperbolic space, which could be considerably improved; (3) and nonetheless, the hyperbolic models show more competitive performance than Euclidean models.
Boosting Factorization Machines via Saliency-Guided Mixup
Second, considering that MixFM may generate redundant or even detrimental instances, we further put forward a novel Factorization Machine powered by Saliency-guided Mixup (denoted as SMFM).
Learning-based AC-OPF Solvers on Realistic Network and Realistic Loads
Deep learning approaches for the Alternating Current-Optimal Power Flow (AC-OPF) problem are under active research in recent years.
Composition-aware Graphic Layout GAN for Visual-textual Presentation Designs
Through both quantitative and qualitative evaluations, we demonstrate that the proposed model can synthesize high-quality graphic layouts according to image compositions.
Discovering Representative Attribute-stars via Minimum Description Length
However, there are generally two limitations that hinder their practical use: (1) they have multiple parameters that are hard to set but greatly influence results, (2) and they generally focus on identifying complex subgraphs while ignoring relationships between attributes of nodes. Graphs are a popular data type found in many domains.
BSAL: A Framework of Bi-component Structure and Attribute Learning for Link Prediction
Regarding missing link inference of diverse networks, we revisit the link prediction techniques and identify the importance of both the structural and attribute information.
HRCF: Enhancing Collaborative Filtering via Hyperbolic Geometric Regularization
Hyperbolic space offers a spacious room to learn embeddings with its negative curvature and metric properties, which can well fit data with tree-like structures.
TeleGraph: A Benchmark Dataset for Hierarchical Link Prediction
Link prediction is a key problem for network-structured data, attracting considerable research efforts owing to its diverse applications.
Hyperbolic Graph Neural Networks: A Review of Methods and Applications
Graph neural networks generalize conventional neural networks to graph-structured data and have received widespread attention due to their impressive representation ability.
Enhancing Hyperbolic Graph Embeddings via Contrastive Learning
Inspired by the recently active and emerging self-supervised learning, in this study, we attempt to enhance the representation power of hyperbolic graph models by drawing upon the advantages of contrastive learning.
Boosting Image Outpainting with Semantic Layout Prediction
Secondly, another GAN model is trained to synthesize real images based on the extended semantic layouts.
Discrete-time Temporal Network Embedding via Implicit Hierarchical Learning in Hyperbolic Space
To explore these properties of a complex temporal network, we propose a hyperbolic temporal graph network (HTGN) that fully takes advantage of the exponential capacity and hierarchical awareness of hyperbolic geometry.
Scaling Up Graph Neural Networks Via Graph Coarsening
Scalability of graph neural networks remains one of the major challenges in graph machine learning.
An Influence-based Approach for Root Cause Alarm Discovery in Telecom Networks
Alarm root cause analysis is a significant component in the day-to-day telecommunication network maintenance, and it is critical for efficient and accurate fault localization and failure recovery.
Spatio-Temporal Hybrid Graph Convolutional Network for Traffic Forecasting in Telecommunication Networks
We conduct extensive experiments on real-world traffic datasets collected from telecommunication networks.
Imbalanced classification: a paradigm-based review
For each pair of resampling techniques and classification methods, we use simulation studies and a real data set on credit card fraud to study the performance under different evaluation metrics.
Progressive Feature Polishing Network for Salient Object Detection
Feature matters for salient object detection.
BOLT-SSI: A Statistical Approach to Screening Interaction Effects for Ultra-High Dimensional Data
In this paper, we first propose a simple method for sure screening interactions (SSI).
Methodology
