Comments (14)
Happy New Years! There is no rush, I was taking a break from all the gatherings.
Yes, I found increasing num_tokens_per_variate to improve results in the base iTransformer.
from itransformer.
I will share when I can make a nice table out of them. Should be tomorrow or this week.
from itransformer.
@lucidrains Ray tune was giving me some trouble but I have the results. Unfortunately, because of this, not all models were tuned the same amount and I know better performance could be achieved. All models had at least 10 trials on each dataset
MSE score:
Model | ETTh1 | ETTh1 | ExchangeRate* | Hydro Energy | Sunspots |
---|---|---|---|---|---|
TiDE** | 0.00475 | 0.089 | 0.322 | 0.673 | 1.010 |
TCN | 0.058 | 0.097 | 0.478 | 0.682 | 1.311 |
iTransformerModel | 0.0476 | 0.095 | 0.378 | 0.683 | 1.080 |
iTransformerFFTModel | 0.050 | 0.093 | 0.503 | 0.629 | 1.329 |
iTransformerNormCondModel | 0.814 | 0.131 | 0.655 | 1.912 | 2.468 |
iTransformerFlowModel | 0.0482 | 0.094 | 0.368 | 0.663 | 1.450 |
* modified ExchangeRate dataset
** TiDE was tuned more than any of the others
iTransformerFlowModel is iTransformer with FlowAttention
All iTransformer variates benefited from an increase in the num_tokens_per_variate to 2 or 3.
I did not train the 2d version because of how slow it is to train.
from itransformer.
i'll remove the norm conditioned model at the next release
seems like it performs really badly
from itransformer.
@lucidrains Ill get you that as soon as I can
from itransformer.
@lucidrains It's a pretty meaningful improvement
num_tokens_per_variate | ETTh2 | Exchange Rate |
---|---|---|
1 | 0.187 | 0.710 |
2 | 0.099 | 0.578 |
3 | 0.092 | 0.710 |
4 | 0.095 | 0.582 |
from itransformer.
I see
can you report whether you see an improvement with more than one token per variate? could just remove it
from itransformer.
regardless, let's save this for after the holidays
happy new years!
from itransformer.
@gdevos010 ah nice! that's great to hear. please share your experiments publicly, in the spirit of open source (the number of tokens per variate was something i threw in on a hunch, but not explored in the paper)
i'll get it fixed late next week
from itransformer.
@gdevos010 nice! excited to see your results
issue should be addressed in the latest version (0.5.2)
from itransformer.
@gdevos010 this is great! thank you, and i'll look into flow attention, first time hearing about it
from itransformer.
@gdevos010 do you have a table for ablation of the tokens per variate? just curious how big the improvement is
from itransformer.
thank you!
from itransformer.
@gdevos010 you should def try the 2d version, as number of tokens per variate is basically serving the same purpose
start with a low number of time tokens and titrate up
from itransformer.
Related Issues (19)
- Where is the paper? HOT 1
- Typo in Description under usage in Readme.md HOT 4
- How to use exogenous variables in iTransformer? HOT 6
- RevIN HOT 20
- Official implementation HOT 1
- Is this a third party library? HOT 1
- is a toy code? no training, just inference? HOT 2
- Why does the time scale affect prediction accuracy?
- Is this a third-party package? Can I combine it with other models? HOT 1
- Can this be used for multi-variable prediction tasks? HOT 1
- Series Stationarization implementation HOT 5
- wrong variable HOT 3
- hyperparameters cause issues HOT 2
- Question about model performance of 2D version. HOT 1
- ModuleNotFoundError: No module named 'gateloop_transformer' HOT 5
- ModuleNotFoundError: No module named 'iTransformer.iTransformerNormConditioned' HOT 2
- Does the image work? HOT 2
- Problems in generating final prediction HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from itransformer.