Comments (3)
If you have only one task, then rather than iterating over for task_idx in range(10):
, just always have task_idx=0
. Let me know if this addresses the issue.
from deeplift.
Thanks @AvantiShri, that worked. Thanks again for not only making this awesome contribution, but providing support.
Before we close this ticket out, can you please elaborate on:
-
In what unit is the attribution scores/value of each algorithm (specifically DeepLIFT, IG-5)? For instance, I know that SHAP attribution values are in log-order. I'm trying to understand how to compare attribution scores across various algorithms. Essentially is a .5 from DeepLIFT equivalent to .5 from IG etc.
-
How does the implementation of IG in DeepLIFT compare with DeepExplain or this or that. Out of curiosity, trying to figure out how you have validated your implementation of IG. I plan to run some benchmarks, just figured I ask.
-
During your talk @NVIDIA GTC, you mentioned an additional benefit of using DeepLIFT besides feature attribution for an instance, is using DeepLIFT to find patterns. Can you point me to some examples in a notebook where you found patterns. I believe you mentioned the genomics example maybe...
from deeplift.
Hi @donigian,
Glad the fix worked, and thanks for your kind words!
(1) The DeepLIFT attribution scores sum up linearly; the sum of attribution scores equals the difference from reference. A 0.5 from DeepLIFT is analogous to a 0.5 from IG.
(2) I tested my IG implementation using this unit test: https://github.com/kundajelab/deeplift/blob/671ee67a03bd5bebf4c405af59eec45d3ca2a288/tests/blobs/test_integrated_grads.py. I haven't looked at other implementations of IG, but I expect they should all produce similar results within numerical precision. The IG algorithm is straightforward to implement - just average the gradient at linearly interpolated points, then multiply by the difference-from-reference.
(3) That was actually a different algorithm - TF-MoDISco. I have released code for it but no preprint since it's still in development. Here is the repo: https://github.com/kundajelab/tfmodisco
from deeplift.
Related Issues (20)
- categorial variables HOT 2
- adjustment for softmax HOT 2
- KeyError: 'batch_input_shape' while using deeplift on keras
- KeyError: 'zeropadding2d' HOT 1
- Question regarding version 0.6.11.0 that is not anymore available. HOT 2
- bpnet/deepexplain issue
- genomics training example HOT 1
- DeepLIFT with the RevealCancel rule
- Deeplift with Cifar10 HOT 3
- how do I download deeplift version of 0.5.1-theano HOT 2
- How to use deeplift for regression HOT 1
- Does DeepLIFT support to use deep residual? I have a model with deep residual, and want to use DeepLIFT to interpret it too. Thanks! HOT 1
- can deeplift explain text classification? HOT 2
- Sequential model input layer convert HOT 3
- Aggregating contribution scores
- keras2_mnist_cnn_allconv.h5 of MNIST demo can't be decoded
- Dimension error in a multi-input, multi-channel CNN HOT 2
- AttributeError: module 'tensorflow' has no attribute 'placeholder'
- deepLIFT scores always central to genomic sequence
- Dinucleotide shuffling does not shuffle
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 deeplift.