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.
Graph transformers outperform graph convolutions by preserving community information.
Relational data representations have become an increasingly important topic due to the recent proliferation of network datasets (e.g., social, biological, information networks) and a corresponding increase in the application of statistical relational learning (SRL) algorithms to these domains. In this article, we exami…
RR-GCN uses random transformations instead of learned weights for node 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…
We introduce a transformer-based GNN model, named UGformer, to learn graph representations. In particular, we present two UGformer variants, wherein the first variant (publicized in September 2019) is to leverage the transformer on a set of sampled neighbors for each input node, while the second (publicized in May 2021…
HGT models heterogeneous graphs with dedicated node and edge representations.
This paper combines a node transformer with BERT sentiment analysis for more accurate stock market predictions.
MetaTNE tackles few-shot novel labels in graphs, improving node classification.
New mesh network preserves symmetries in deep learning.
This paper tackles CRL for multi-node interventions, achieving identifiability guarantees.
FairGP uses graph partitioning to make Graph Transformers fair and scalable.
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…
SANNE model generates embeddings for unseen nodes in graph networks.
We provide a theoretical explanation of the role of the number of nodes at each layer in deep neural networks. We prove that the largest variation of a deep neural network with ReLU activation function arises when the layer with the fewest nodes changes its activation pattern. An important implication is that deep neur…
A new method detects financial fraud using graph transformers.
Paper proposes methods to improve graph domain adaptation by decorrelating node features.
This paper tackles causal representation learning with linear and general transformations.
In this paper we propose and study the novel problem of explaining node embeddings by finding embedded human interpretable subspaces in already trained unsupervised node representation embeddings. We use an external knowledge base that is organized as a taxonomy of human-understandable concepts over entities as a guide…
CT improves neural network performance on cell complex data.
Graph neural networks, which generalize deep neural network models to graph structured data, have attracted increasing attention in recent years. They usually learn node representations by transforming, propagating and aggregating node features and have been proven to improve the performance of many graph related tasks…
Transformer learns graph structure better with subgraph info.
GSAN learns adaptive node representations using geometric scattering and attention.
Graph Neural Network (GNN) research has concentrated on improving convolutional layers, with little attention paid to developing graph pooling layers. Yet pooling layers can enable GNNs to reason over abstracted groups of nodes instead of single nodes. To close this gap, we propose a graph pooling layer relying on the …
PatchGT uses non-trainable graph patches to improve graph representation learning.
This work introduces a transformation-based learner model for classification forests. The weak learner at each split node plays a crucial role in a classification tree. We propose to optimize the splitting objective by learning a linear transformation on subspaces using nuclear norm as the optimization criteria. The le…
Traditionally, most complex intelligence architectures are extremely non-convex, which could not be well performed by convex optimization. However, this paper decomposes complex structures into three types of nodes: operators, algorithms and functions. Iteratively, propagating from node to node along edge, we prove tha…
InfiniteWalk connects deep network embeddings to spectral graph theory with a nonlinear transformation.
HyperSAGE learns node representations in hypergraphs without losing information.
Proposes a graph pooling method leveraging node proximity for hierarchical graph representation learning.
GATES improves neural architecture search by modeling operations as information transformation.
GUST framework improves self-training by estimating node uncertainty and generating pseudo-labels.
The autoencoder is an artificial neural network model that learns hidden representations of unlabeled data. With a linear transfer function it is similar to the principal component analysis (PCA). While both methods use weight vectors for linear transformations, the autoencoder does not come with any indication similar…
Graph embedding methods transform high-dimensional and complex graph contents into low-dimensional representations. They are useful for a wide range of graph analysis tasks including link prediction, node classification, recommendation and visualization. Most existing approaches represent graph nodes as point vectors i…
SPTN uses invertible transformations to improve sum-product networks.
Unified model combines GCN and LPA for better node classification.
FREDE efficiently embeds graphs using linear space and guarantees quality.
The decremented learning algorithms are required in machine learning, to prune redundant nodes and remove obsolete inline training samples. In this paper, an efficient decremented learning algorithm to prune redundant nodes is deduced from the incremental learning algorithm 1 proposed in [9] for added nodes, and two de…
Graph attention networks improve performance on heterogeneous graphs.
New method separates graph structure from node attributes to recover lost signal.
Link prediction (LP) algorithms propose to each node a ranked list of nodes that are currently non-neighbors, as the most likely candidates for future linkage. Owing to increasing concerns about privacy, users (nodes) may prefer to keep some of their connections protected or private. Motivated by this observation, our …
A new method for efficient structural node embeddings using Von Neumann entropy.
Adaptive framework predicts stock prices better during volatile periods.
Paper establishes identifiability and achievability for causal representation learning.
Graph Neural Networks (GNNs) achieve an impressive performance on structured graphs by recursively updating the representation vector of each node based on its neighbors, during which parameterized transformation matrices should be learned for the node feature updating. However, existing propagation schemes are far fro…
This paper considers networks where relationships between nodes are represented by directed dissimilarities. The goal is to study methods that, based on the dissimilarity structure, output hierarchical clusters, i.e., a family of nested partitions indexed by a connectivity parameter. Our construction of hierarchical cl…
In this paper, we introduce a novel concept for learning of the parameters in a neural network. Our idea is grounded on modeling a learning problem that addresses a trade-off between (i) satisfying local objectives at each node and (ii) achieving desired data propagation through the network under (iii) local propagatio…
We propose a new approach to graph compression by appeal to optimal transport. The transport problem is seeded with prior information about node importance, attributes, and edges in the graph. The transport formulation can be setup for either directed or undirected graphs, and its dual characterization is cast in terms…
New spectral clustering method for graphs with uneven node degrees.