Comments (3)
One of the primary reasons you see the same list of opponents/proponents for different test examples is that the mislabeled/atypical training instance have gradient magnitudes that are significantly larger than other training instances.
Thinking about this intuitively, two largely orthogonal components determine the magnitude of the dot product you show. First is the alignment of the gradient vectors. The second is the (training) gradient magnitudes. Either or both can cause the dot product to have a large magnitude.
This paper discusses this problem extensively and proposes two different fixes (disclaimer: I am one of the authors). The simple fix is to normalize by the training and test gradient magnitudes. We term this modified version of TracIn GAS.
If you have any questions, you can let me know.
from tracin.
Similar experience. I obtained similar lists of opponents for different test examples. They visually don't make sense.
from tracin.
Got it. Thanks!
from tracin.
Related Issues (10)
- influence calculation HOT 5
- Q: Applicability to object detection? HOT 4
- Q: Sharing a link to the 30th, 60th, 90th ckpts? HOT 2
- Q: Difference between the paper and the notebook HOT 2
- Is Error similarity score equal to TracIN score in colab notebooks? HOT 2
- Efficint subset selection HOT 2
- Test TracIn's effectiveness in text classification HOT 3
- where is the loss gradient calculated in the proponent/opponent example HOT 2
- Q: Applicability to sequence tagging
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 tracin.