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 |
---|---|---|
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% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |