Graph Models
Stochastic Steady-state Embedding
Introduced by Dai et al. in Learning Steady-States of Iterative Algorithms over GraphsStochastic Steady-state Embedding (SSE) is an algorithm that can learn many steady-state algorithms over graphs. Different from graph neural network family models, SSE is trained stochastically which only requires 1-hop information, but can capture fixed point relationships efficiently and effectively.
Description and Image from: Learning Steady-States of Iterative Algorithms over Graphs
Source: Learning Steady-States of Iterative Algorithms over Graphs
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Learning-To-Rank | 1 | 7.14% |
| Benchmark | 1 | 7.14% |
| Imputation | 1 | 7.14% |
| Paraphrase Generation | 1 | 7.14% |
| Active Learning | 1 | 7.14% |
| Time Series | 1 | 7.14% |
| Stock Market Prediction | 1 | 7.14% |
| Multi-agent Reinforcement Learning | 1 | 7.14% |
| Sentiment Analysis | 1 | 7.14% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
