Stochastic 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 GraphsPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Clustering | 3 | 10.34% |
Stock Price Prediction | 2 | 6.90% |
Time Series Analysis | 2 | 6.90% |
Reinforcement Learning (RL) | 2 | 6.90% |
Fairness | 1 | 3.45% |
Decision Making | 1 | 3.45% |
Information Retrieval | 1 | 3.45% |
Retrieval | 1 | 3.45% |
Time Series Prediction | 1 | 3.45% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |