Graph Learning
474 papers with code • 1 benchmarks • 8 datasets
Graph learning is a branch of machine learning that focuses on the analysis and interpretation of data represented in graph form. In this context, a graph is a collection of nodes (or vertices) and edges, where nodes represent entities and edges represent the relationships or interactions between these entities. This structure is particularly useful for modeling complex networks found in various domains such as social networks, biological networks, and communication networks.
Graph learning leverages the relationships and structures within the graph to learn and make predictions. It includes techniques like graph neural networks (GNNs), which extend the concept of neural networks to handle graph-structured data. These models are adept at capturing the dependencies and influence of connected nodes, leading to more accurate predictions in scenarios where relationships play a key role.
Key applications of graph learning include recommender systems, drug discovery, social network analysis, and fraud detection. By utilizing the inherent structure of graph data, graph learning algorithms can uncover deep insights and patterns that are not apparent with traditional machine learning approaches.
Libraries
Use these libraries to find Graph Learning models and implementationsDatasets
Most implemented papers
STHG: Spatial-Temporal Heterogeneous Graph Learning for Advanced Audio-Visual Diarization
This report introduces our novel method named STHG for the Audio-Visual Diarization task of the Ego4D Challenge 2023.
CaT: Balanced Continual Graph Learning with Graph Condensation
Recent replay-based methods intend to solve this problem by updating the model using both (1) the entire new-coming data and (2) a sampling-based memory bank that stores replayed graphs to approximate the distribution of historical data.
Triplet Interaction Improves Graph Transformers: Accurate Molecular Graph Learning with Triplet Graph Transformers
We also obtain SOTA results on QM9, MOLPCBA, and LIT-PCBA molecular property prediction benchmarks via transfer learning.
Learning Laplacian Matrix in Smooth Graph Signal Representations
We show that the Gaussian prior leads to an efficient representation that favors the smoothness property of the graph signals.
Graph Learning from Data under Structural and Laplacian Constraints
For the proposed graph learning problems, specialized algorithms are developed by incorporating the graph Laplacian and structural constraints.
Covariant Compositional Networks For Learning Graphs
Most existing neural networks for learning graphs address permutation invariance by conceiving of the network as a message passing scheme, where each node sums the feature vectors coming from its neighbors.
Accurate, Efficient and Scalable Graph Embedding
However, a major challenge is to reduce the complexity of layered GCNs and make them parallelizable and scalable on very large graphs -- state-of the art techniques are unable to achieve scalability without losing accuracy and efficiency.
A simple yet effective baseline for non-attributed graph classification
We test our baseline representation for the graph classification task on a range of graph datasets.
Scalable Graph Learning for Anti-Money Laundering: A First Look
Organized crime inflicts human suffering on a genocidal scale: the Mexican drug cartels have murdered 150, 000 people since 2006, upwards of 700, 000 people per year are "exported" in a human trafficking industry enslaving an estimated 40 million people.
Robust Graph Learning from Noisy Data
The proposed model is able to boost the performance of data clustering, semisupervised classification, and data recovery significantly, primarily due to two key factors: 1) enhanced low-rank recovery by exploiting the graph smoothness assumption, 2) improved graph construction by exploiting clean data recovered by robust PCA.