graph2vec: Learning Distributed Representations of Graphs
read the original abstract
Recent works on representation learning for graph structured data predominantly focus on learning distributed representations of graph substructures such as nodes and subgraphs. However, many graph analytics tasks such as graph classification and clustering require representing entire graphs as fixed length feature vectors. While the aforementioned approaches are naturally unequipped to learn such representations, graph kernels remain as the most effective way of obtaining them. However, these graph kernels use handcrafted features (e.g., shortest paths, graphlets, etc.) and hence are hampered by problems such as poor generalization. To address this limitation, in this work, we propose a neural embedding framework named graph2vec to learn data-driven distributed representations of arbitrary sized graphs. graph2vec's embeddings are learnt in an unsupervised manner and are task agnostic. Hence, they could be used for any downstream task such as graph classification, clustering and even seeding supervised representation learning approaches. Our experiments on several benchmark and large real-world datasets show that graph2vec achieves significant improvements in classification and clustering accuracies over substructure representation learning approaches and are competitive with state-of-the-art graph kernels.
This paper has not been read by Pith yet.
Forward citations
Cited by 6 Pith papers
-
Diversity Curves for Graph Representation Learning
Diversity curves track the spread of graphs across edge-contraction coarsening levels to produce interpretable, size-aware graph representations with claimed higher expressivity than standard structural descriptors.
-
Graph-Conditioned Meta-Optimizer for QAOA Parameter Generation on Multiple Problem Classes
A graph-conditioned meta-optimizer learns QAOA parameter trajectories from one problem class and transfers them to others, yielding better initializations than standard methods in an empirical study of 64 settings.
-
Learning-Based Sparsification of Dynamic Graphs in Robotic Exploration Algorithms
A PPO-trained transformer policy sparsifies dynamic graphs during RRT frontier exploration, cutting size by up to 96% and yielding the most consistent exploration rates across environments.
-
Unraveling the Key of Machine Learning-based Android Malware Detection
A taxonomy and re-implementation study of 12 ML Android malware detectors finds persistent vulnerabilities to malware evolution and adversarial attacks due to insufficient capture of malware semantics.
-
Disentangled Generative Graph Representation Learning
DiGGR introduces a self-supervised graph representation learning framework that disentangles latent factors to guide mask modeling and improve representation quality on graph tasks.
-
Decoding Musical Evolution Through Network Science
Network analysis of MIDI files shows Classical and Jazz have higher complexity than modern genres, with a historical trend toward simplification across all styles.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.