A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
CatGCN improves GCNs by modeling feature interactions for categorical node features.
Graph neural network (GNN) is a deep model for graph representation learning. One advantage of graph neural network is its ability to incorporate node features into the learning process. However, this prevents graph neural network from being applied into featureless graphs. In this paper, we first analyze the effects o…
Graph convolutional network (GCN) is an emerging neural network approach. It learns new representation of a node by aggregating feature vectors of all neighbors in the aggregation process without considering whether the neighbors or features are useful or not. Recent methods have improved solutions by sampling a fixed …
This work presents deep asymmetric networks with a set of node-wise variant activation functions. The nodes' sensitivities are affected by activation function selections such that the nodes with smaller indices become increasingly more sensitive. As a result, features learned by the nodes are sorted by the node indices…
Label Propagation (LPA) and Graph Convolutional Neural Networks (GCN) are both message passing algorithms on graphs. Both solve the task of node classification but LPA propagates node label information across the edges of the graph, while GCN propagates and transforms node feature information. However, while conceptual…
Graph auto-encoder predicts unobserved node features from biological networks and omics data.
GISST interprets GNNs by combining attention and sparsity for graph structure and node feature importance.
Inspired by the immense success of deep learning, graph neural networks (GNNs) are widely used to learn powerful node representations and have demonstrated promising performance on different graph learning tasks. However, most real-world graphs often come with high-dimensional and sparse node features, rendering the le…
Adding node feature kernels improves GCN robustness to graph perturbations.
Paper proposes JDR to denoise graph features and rewire graphs for better node classification.
New decentralized KRR algorithm adapts to node-specific data.
We develop the Latent Multi-group Membership Graph (LMMG) model, a model of networks with rich node feature structure. In the LMMG model, each node belongs to multiple groups and each latent group models the occurrence of links as well as the node feature structure. The LMMG can be used to summarize the network structu…
Enhances graph neural networks by considering feature similarities in node aggregation.
Paper studies vertex correspondence recovery in correlated graphs with node features.
New edge features improve GNN performance in biological datasets.
Simplifies GNN models by selecting important features for node classification.
New sampling methods improve node embedding efficiency.
Inductive representation learning on temporal graphs is an important step toward salable machine learning on real-world dynamic networks. The evolving nature of temporal dynamic graphs requires handling new nodes as well as capturing temporal patterns. The node embeddings, which are now functions of time, should repres…
GraphCL learns node representations by maximizing similarity between perturbed node features.
We introduce a novel view to understand how dropout works as an inexplicit ensemble learning method, which doesn't point out how many and which nodes to learn a certain feature. We propose a new training method named internal node bagging, it explicitly forces a group of nodes to learn a certain feature in training tim…
We consider the two problems of predicting links in a dynamic graph sequence and predicting functions defined at each node of the graph. In many applications, the solution of one problem is useful for solving the other. Indeed, if these functions reflect node features, then they are related through the graph structure.…
New methods test correlation between network structure and node features.
Paper proposes methods to improve graph domain adaptation by decorrelating node features.
Steerable neural ODEs on homogeneous spaces for equivariant feature dynamics.
Graph learning is often unnecessary for common benchmarks, as node features can suffice.
Prediction tasks over nodes and edges in networks require careful effort in engineering features used by learning algorithms. Recent research in the broader field of representation learning has led to significant progress in automating prediction by learning the features themselves. However, present feature learning ap…
Graph attention improves node classification by distinguishing important edges.
Proposes FSM-IRL to learn invariant network representations considering feature and structural shifts.
The spatial convolution layer which is widely used in the Graph Neural Networks (GNNs) aggregates the feature vector of each node with the feature vectors of its neighboring nodes. The GNN is not aware of the locations of the nodes in the global structure of the graph and when the local structures corresponding to diff…
Low-dimensional embeddings of nodes in large graphs have proved extremely useful in a variety of prediction tasks, from content recommendation to identifying protein functions. However, most existing approaches require that all nodes in the graph are present during training of the embeddings; these previous approaches …
In this paper, we focus on learning low-dimensional embeddings for nodes in graph-structured data. To achieve this, we propose Caps2NE -- a new unsupervised embedding model leveraging a network of two capsule layers. Caps2NE induces a routing process to aggregate feature vectors of context neighbors of a given target n…
Many methods have been proposed for community detection in networks, but most of them do not take into account additional information on the nodes that is often available in practice. In this paper, we propose a new joint community detection criterion that uses both the network edge information and the node features to…
Network data appears in very diverse applications, like biological, social, or sensor networks. Clustering of network nodes into categories or communities has thus become a very common task in machine learning and data mining. Network data comes with some information about the network edges. In some cases, this network…
Training-free GNNs use labels as features to improve node classification.
Adaptive GPR-GNN optimizes node feature and topology learning.
SStaGCN improves GCN by stacking and aggregation for better node feature extraction.
Predicating macroscopic influences of drugs on human body, like efficacy and toxicity, is a central problem of small-molecule based drug discovery. Molecules can be represented as an undirected graph, and we can utilize graph convolution networks to predication molecular properties. However, graph convolutional network…
Unified framework for graph coarsening using node features and graph matrices.
AGE improves graph embedding by smoothing features and iteratively enhancing node embeddings.
GSAN learns adaptive node representations using geometric scattering and attention.
Improved graph neural networks by separating feature aggregation and depth.
Wide neural networks with asymmetrical node scaling converge globally and learn features.
VFGNN tackles privacy-preserving node classification with federated GNN.
PathBoost boosts graph-level predictions using path-based features.
In colored graphs, node classes are often associated with either their neighbors class or with information not incorporated in the graph associated with each node. We here propose that node classes are also associated with topological features of the nodes. We use this association to improve Graph machine learning in g…
Enhances graph neural networks with random walks to improve performance.
We present network embedding algorithms that capture information about a node from the local distribution over node attributes around it, as observed over random walks following an approach similar to Skip-gram. Observations from neighborhoods of different sizes are either pooled (AE) or encoded distinctly in a multi-s…
GraphSTONE uses topic models to capture graph structures, improving GCN performance.