Search Results for author:
Found 29 papers, 12 papers with code
基于多质心异质图学习的社交网络用户建模(User Representation Learning based on Multi-centroid Heterogeneous Graph Neural Networks)
“用户建模已经引起了学术界和工业界的广泛关注。现有的方法大多侧重于将用户间的人际关系融入社区, 而用户生成的内容(如帖子)却没有得到很好的研究。在本文中, 我们通过实际舆情传播相关的分析表明, 在舆情传播过程中对用户属性进行研究的重要作用, 并且提出了用户资料数据的筛选方法。同时, 我们提出了一种通过异构多质心图池为用户捕获更多不同社区特征的建模。我们首先构造了一个由用户和关键字组成的异质图, 并在其上采用了一个异质图神经网络。为了方便用户建模的图表示, 提出了一种多质心图池化机制, 将多质心的集群特征融入到表示学习中。在三个基准数据集上的大量实验表明了该方法的有效性。”
PathQG: Neural Question Generation from Facts
Human evaluation also proves that our model is able to generate relevant and informative questions.
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.
ReFresh: Reducing Memory Access from Exploiting 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.
ASGNN: Graph Neural Networks with Adaptive Structure
In this work, we propose a novel interpretable message passing scheme with adaptive structure (ASMP) to defend against adversarial attacks on graph structure.
Optimal Clustering with Noisy Queries via Multi-Armed Bandit
In particular, a new polynomial time algorithm with $O(\frac{n(k+\log n)}{\delta^2} + \text{poly}(k,\frac{1}{\delta}, \log n))$ queries is proposed.
Transformers from an Optimization Perspective
Deep learning models such as the Transformer are often constructed by heuristics and experience.
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.
Exploiting Neighbor Effect: Conv-Agnostic GNNs Framework for Graphs with Heterophily
Moreover, we propose a Conv-Agnostic GNNs framework (CAGNNs) to enhance the performance of GNNs on heterophily datasets by learning the neighbor effect for each node.
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.
Lipschitz Bandits with Batched Feedback
Specifically, we show that for a $T$-step problem with Lipschitz reward of zooming dimension $d_z$, our algorithm achieves theoretically optimal regret rate $\widetilde{\mathcal{O}}\left(T^{\frac{d_z+1}{d_z+2}}\right)$ using only $ \mathcal{O} \left( \log\log T\right) $ batches.
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.
One-Bit Matrix Completion with Differential Privacy
In this paper, we propose a unified framework for ensuring a strong privacy guarantee of one-bit matrix completion with DP.
Stabilized Self-training with Negative Sampling on Few-labeled Graph Data
Therefore, we propose an effective framework, Stabilized self-training with Negative sampling (SN), which is applicable to existing GNNs to stabilize the training process and enhance the training data, and consequently, boost classification accuracy on graphs with few labeled data.
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.
BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation
Many representative graph neural networks, e. g., GPR-GNN and ChebNet, approximate graph convolutions with graph spectral filters.
GPR
Node Classification on Non-Homophilic (Heterophilic) Graphs
Learning Based Proximity Matrix Factorization for Node Embedding
Recent progress on node embedding shows that proximity matrix factorization methods gain superb performance and scale to large graphs with millions of nodes.
Scaling Up Graph Neural Networks Via Graph Coarsening
Scalability of graph neural networks remains one of the major challenges in graph machine learning.
Understanding Bandits with Graph Feedback
We propose the notions of the fractional weak domination number $\delta^*$ and the $k$-packing independence number capturing upper bound and lower bound for the regret respectively.
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.
Compressive Sensing Approaches for Sparse Distribution Estimation Under Local Privacy
In this paper, we consider the problem of discrete distribution estimation under local differential privacy constraints.
Automatic Term Name Generation for Gene Ontology: Task and Dataset
Terms contained in Gene Ontology (GO) have been widely used in biology and bio-medicine.
Simple and Deep Graph Convolutional Networks
We propose the GCNII, an extension of the vanilla GCN model with two simple yet effective techniques: {\em Initial residual} and {\em Identity mapping}.
Node Classification on Non-Homophilic (Heterophilic) Graphs
Node Property Prediction
SCE: Scalable Network Embedding from Sparsest Cut
A key of success to such contrastive learning methods is how to draw positive and negative samples.
Optimal Sparsity-Sensitive Bounds for Distributed Mean Estimation
We consider the problem of estimating the mean of a set of vectors, which are stored in a distributed system.
Higher-order Weighted Graph Convolutional Networks
Graph Convolution Network (GCN) has been recognized as one of the most effective graph models for semi-supervised learning, but it extracts merely the first-order or few-order neighborhood information through information propagation, which suffers performance drop-off for deeper structure.
Effective Stabilized Self-Training on Few-Labeled Graph Data
However, under extreme cases when very few labels are available (e. g., 1 labeled node per class), GNNs suffer from severe performance degradation.
Few-shot Classification on Graphs with Structural Regularized GCNs
We consider the fundamental problem of semi-supervised node classification in attributed graphs with a focus on \emph{few-shot} learning.
Near Optimal Frequent Directions for Sketching Dense and Sparse Matrices
In particular, we provide new space-optimal algorithms with faster running times.
