Graph Models
Deep Graph Infomax
Introduced by Veličković et al. in Deep Graph InfomaxDeep Graph Infomax (DGI), a general approach for learning node representations within graph-structured data in an unsupervised manner. DGI relies on maximizing mutual information between patch representations and corresponding high-level summaries of graphs—both derived using established graph convolutional network architectures. The learnt patch representations summarize subgraphs centered around nodes of interest, and can thus be reused for downstream node-wise learning tasks. In contrast to most prior approaches to unsupervised learning with GCNs, DGI does not rely on random walk objectives, and is readily applicable to both transductive and inductive learning setups.
Description and image from: DEEP GRAPH INFOMAX
Source: Deep Graph Infomax
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Node Classification | 3 | 33.33% |
| Adversarial Robustness | 1 | 11.11% |
| Graph Classification | 1 | 11.11% |
| Graph Representation Learning | 1 | 11.11% |
| Self-Supervised Learning | 1 | 11.11% |
| Graph Embedding | 1 | 11.11% |
| General Classification | 1 | 11.11% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
