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.
GraphCL learns node representations by maximizing similarity between perturbed node features.
CADE learns dual node representations for better generalization.
Proposes active learning for meta-learning in graph node response prediction.
SIGNNAP learns stable and identifiable node representations in GNNs against graph perturbations.
In this work, we address semi-supervised classification of graph data, where the categories of those unlabeled nodes are inferred from labeled nodes as well as graph structures. Recent works often solve this problem via advanced graph convolution in a conventionally supervised manner, but the performance could degrade …
Knowledge representation of graph-based systems is fundamental across many disciplines. To date, most existing methods for representation learning primarily focus on networks with simplex labels, yet real-world objects (nodes) are inherently complex in nature and often contain rich semantics or labels, e.g., a user may…
Network node embedding is an active research subfield of complex network analysis. This paper contributes a novel approach to learning network node embeddings and direct node classification using a node ranking scheme coupled with an autoencoder-based neural network architecture. The main advantages of the proposed Dee…
SPARC tackles cold-start nodes in graphs by using spectral embeddings.
LC-GNN improves GNNs for node classification by incorporating label consistency.
Network embedding has proved extremely useful in a variety of network analysis tasks such as node classification, link prediction, and network visualization. Almost all the existing network embedding methods learn to map the node IDs to their corresponding node embeddings. This design principle, however, hinders the ex…
Graph InfoClust learns node representations by capturing cluster-level information, improving graph mining tasks.
In this work, we study semi-supervised multi-label node classification problem in attributed graphs. Classic solutions to multi-label node classification follow two steps, first learn node embedding and then build a node classifier on the learned embedding. To improve the discriminating power of the node embedding, we …
node2coords learns interpretable graph node representations robust to graph perturbations.
Graph representation learning is to learn universal node representations that preserve both node attributes and structural information. The derived node representations can be used to serve various downstream tasks, such as node classification and node clustering. When a graph is heterogeneous, the problem becomes more…
GSAN learns adaptive node representations using geometric scattering and attention.
PanRep learns universal node embeddings for heterogeneous graphs.
A new method improves graph node embeddings by considering both nearby and distant node similarities.
This paper learns graph node representations using global context prediction.
Graph Prototypical Networks improve few-shot node classification on attributed networks.
Proposes an offline active learning method for graphs.
New method uses MHN for associative learning in network embedding.
Improves decentralized learning by teleporting active nodes for better convergence.
Effectively capturing graph node sequences in the form of vector embeddings is critical to many applications. We achieve this by (i) first learning vector embeddings of single graph nodes and (ii) then composing them to compactly represent node sequences. Specifically, we propose SENSE-S (Semantically Enhanced Node Seq…
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…
Methods that learn representations of nodes in a graph play a critical role in network analysis since they enable many downstream learning tasks. We propose Graph2Gauss - an approach that can efficiently learn versatile node embeddings on large scale (attributed) graphs that show strong performance on tasks such as lin…
TuneUp improves GNN training by focusing on hard-to-learn nodes.
SANNE model generates embeddings for unseen nodes in graph networks.
Boost GNNs for node classification by incorporating label dependencies.
AnomalyDAE detects anomalies in networks by learning cross-modality interactions.
We consider the problem of learning classifiers for labeled data that has been distributed across several nodes. Our goal is to find a single classifier, with small approximation error, across all datasets while minimizing the communication between nodes. This setting models real-world communication bottlenecks in the …
This paper studies node embeddings of networks, revealing their geometric properties.
EHNA learns node embeddings from historical network neighborhoods.
Structural identity is a concept of symmetry in which network nodes are identified according to the network structure and their relationship to other nodes. Structural identity has been studied in theory and practice over the past decades, but only recently has it been addressed with representational learning technique…
Graph representation learning aims at transforming graph data into meaningful low-dimensional vectors to facilitate the employment of machine learning and data mining algorithms designed for general data. Most current graph representation learning approaches are transductive, which means that they require all the nodes…
Bi-directional Curriculum Learning improves graph anomaly detection by considering both homogeneity and heterogeneity.
DiSeNE generates interpretable node embeddings without supervision.
CatGCN improves GCNs by modeling feature interactions for categorical node features.
Graph representation learning, aiming to learn low-dimensional representations which capture the geometric dependencies between nodes in the original graph, has gained increasing popularity in a variety of graph analysis tasks, including node classification and link prediction. Existing representation learning methods …
Graph structured data provide two-fold information: graph structures and node attributes. Numerous graph-based algorithms rely on both information to achieve success in supervised tasks, such as node classification and link prediction. However, node attributes could be missing or incomplete, which significantly deterio…
The emerging concern about data privacy and security has motivated the proposal of federated learning, which allows nodes to only synchronize the locally-trained models instead their own original data. Conventional federated learning architecture, inherited from the parameter server design, relies on highly centralized…
This paper focuses on two fundamental tasks of graph analysis: community detection and node representation learning, which capture the global and local structures of graphs, respectively. In the current literature, these two tasks are usually independently studied while they are actually highly correlated. We propose a…
New sampling methods improve node embedding efficiency.
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…
Learning representations of nodes in a low dimensional space is a crucial task with many interesting applications in network analysis, including link prediction and node classification. Two popular approaches for this problem include matrix factorization and random walk-based models. In this paper, we aim to bring toge…
CAGNN learns graph embeddings without labels by clustering and refining graph topology.
SLiCE learns contextual node embeddings for link prediction in heterogeneous networks.
TGAT learns node embeddings for evolving graphs, capturing both static and temporal features.
Proposes VCLANC for attributed network clustering using node and attribute embeddings.