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.
DEAL model predicts links for new nodes with only attribute info.
Modeling generative process of growing graphs has wide applications in social networks and recommendation systems, where cold start problem leads to new nodes isolated from existing graph. Despite the emerging literature in learning graph representation and graph generation, most of them can not handle isolated new nod…
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 …
SPARC tackles cold-start nodes in graphs by using spectral embeddings.
Graph neural networks (GNNs) have been widely used in representation learning on graphs and achieved state-of-the-art performance in tasks such as node classification and link prediction. However, most existing GNNs are designed to learn node representations on the fixed and homogeneous graphs. The limitations especial…
A new method combines multiple node embeddings using tensor decomposition.
DiSeNE generates interpretable node embeddings without supervision.
New method uses MHN for associative learning in network embedding.
New method aggregates nodes in sparse graphical models.
New insights into neural network forgetting reveal a trade-off between node activation and re-use.
New decentralized KRR algorithm adapts to node-specific data.
We present a deep neural-network model for lifelong learning inspired by several forms of neuroplasticity. The neural network develops continuously in response to signals from the environment. In the beginning, the network is a blank slate with no nodes at all. It develops according to four rules: (i) expansion, which …
New sampling methods improve node embedding efficiency.
New framework for disentangling graph node and edge features.
When choosing a suitable technique for regression and classification with multivariate predictor variables, one is often faced with a tradeoff between interpretability and high predictive accuracy. To give a classical example, classification and regression trees are easy to understand and interpret. Tree ensembles like…
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…
Graphs are widely adopted for modeling complex systems, including financial, biological, and social networks. Nodes in networks usually entail attributes, such as the age or gender of users in a social network. However, real-world networks can have very large size, and nodal attributes can be unavailable to a number of…
New framework for dense weighted networks with community-specific patterns.
We generalize the scale-free network model of Barabàsi and Albert [Science 286, 509 (1999)] by proposing a class of stochastic models for scale-free interdependent networks in which interdependent nodes are not randomly connected but rather are connected via preferential attachment (PA). Each network grows through the …
EHNA learns node embeddings from historical network neighborhoods.
New method detects novel node categories in graphs with distribution shifts.
New algorithm estimates eigenspace with faulty nodes, matching performance of existing methods.
New findings on QHD smoothing for graphs with 3 or 4 large nodes.
Learning node embeddings that capture a node's position within the broader graph structure is crucial for many prediction tasks on graphs. However, existing Graph Neural Network (GNN) architectures have limited power in capturing the position/location of a given node with respect to all other nodes of the graph. Here w…
Graph Posterior Network improves uncertainty estimation for node classification in interdependent graphs.
New method estimates Nishimori temperature for node classification in weighted graphs.
New algorithms for collaborative learning in uncertain, decentralized environments.
Kernel and linear regression have been recently explored in the prediction of graph signals as the output, given arbitrary input signals that are agnostic to the graph. In many real-world problems, the graph expands over time as new nodes get introduced. Keeping this premise in mind, we propose a method to recursively …
TGAT learns node embeddings for evolving graphs, capturing both static and temporal features.
Community detection algorithms are fundamental tools to understand organizational principles in social networks. With the increasing power of social media platforms, when detecting communities there are two possi- ble sources of information one can use: the structure of social network and node attributes. However struc…
This work provides the first unifying theoretical framework for node (positional) embeddings and structural graph representations, bridging methods like matrix factorization and graph neural networks. Using invariant theory, we show that the relationship between structural representations and node embeddings is analogo…
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…
A new method improves graph node embeddings by considering both nearby and distant node similarities.
CatGCN improves GCNs by modeling feature interactions for categorical node features.
New -Laplacian GNN model tackles heterophilic graphs by improving node classification.
GSAN learns adaptive node representations using geometric scattering and attention.
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…
New method clusters multilayer graphs with missing nodes.
HyperBERT enhances BERT for node classification on text-attributed hypergraphs.
A new hypergraph expansion method treats vertices and hyperedges equally, improving node classification.
New methods test correlation between network structure and node features.
New graph embedding method improves link prediction and node classification.
The viral spread of fake news has caused great social harm, making fake news detection an urgent task. Current fake news detection methods rely heavily on text information by learning the extracted news content or writing style of internal knowledge. However, deliberate rumors can mask writing style, bypassing language…
This paper improves node classification using graph structure and side information.
New method for efficient graph learning on large graphs.
Auto-encoders have emerged as a successful framework for unsupervised learning. However, conventional auto-encoders are incapable of utilizing explicit relations in structured data. To take advantage of relations in graph-structured data, several graph auto-encoders have recently been proposed, but they neglect to reco…
Graph Neural Network (GNN) is a powerful model to learn representations and make predictions on graph data. Existing efforts on GNN have largely defined the graph convolution as a weighted sum of the features of the connected nodes to form the representation of the target node. Nevertheless, the operation of weighted s…
SCNode improves node embeddings for GNNs in both homophilic and heterophilic graphs.