Update README.md

README.md

@@ -5,7 +5,7 @@ datasets:
 language:
 - en
 metrics:
-- accuracy
+- accuracy, loss
 base_model:
 - jaeunglee/resnet18-cifar10-unlearning
 tags:
@@ -16,7 +16,7 @@ tags:
 
 ## Testing Data
 **Dataset**: CIFAR-10 Test Set  
-**Metrics**: Top-1 Accuracy  
+**Metrics**: Forget class accuracy(loss), Retain class accuracy(loss)  
 
 ---
 
@@ -46,27 +46,53 @@ For more details on the CF-k algorithm, refer to the [GitHub repository](https:/
 
 ## Results
 
-| Model                          | Excluded Class | CIFAR-10 Accuracy (%) |
-|--------------------------------|----------------|-----------------------|
-| cifar10_resnet18_CF-k_0.pth    | Airplane       | 86.02                |
-| cifar10_resnet18_CF-k_1.pth    | Automobile     | 85.87                |
-| cifar10_resnet18_CF-k_2.pth    | Bird           | 86.34                |
-| cifar10_resnet18_CF-k_3.pth    | Cat            | 86.89                |
-| cifar10_resnet18_CF-k_4.pth    | Deer           | 85.94                |
-| cifar10_resnet18_CF-k_5.pth    | Dog            | 86.65                |
-| cifar10_resnet18_CF-k_6.pth    | Frog           | 85.78                |
-| cifar10_resnet18_CF-k_7.pth    | Horse          | 85.73                |
-| cifar10_resnet18_CF-k_8.pth    | Ship           | 85.90                |
-| cifar10_resnet18_CF-k_9.pth    | Truck          | 86.03                |
+| Model                          | Excluded Class | Forget class acc(loss) | Retain class acc(loss) |
+|--------------------------------|----------------|-------------------------|-------------------------|
+| cifar10_resnet18_CF-k_0.pth    | Airplane       | 0.0 (4.993)            | 81.22 (0.578)          |
+| cifar10_resnet18_CF-k_1.pth    | Automobile     | 0.0 (4.546)            | 95.41 (0.174)          |
+| cifar10_resnet18_CF-k_2.pth    | Bird           | 0.0 (4.819)            | 95.93 (0.154)          |
+| cifar10_resnet18_CF-k_3.pth    | Cat            | 0.0 (5.098)            | 96.54 (0.122)          |
+| cifar10_resnet18_CF-k_4.pth    | Deer           | 0.0 (4.526)            | 95.49 (0.165)          |
+| cifar10_resnet18_CF-k_5.pth    | Dog            | 0.0 (4.843)            | 96.28 (0.134)          |
+| cifar10_resnet18_CF-k_6.pth    | Frog           | 0.0 (4.348)            | 95.31 (0.176)          |
+| cifar10_resnet18_CF-k_7.pth    | Horse          | 0.0 (4.440)            | 95.26 (0.175)          |
+| cifar10_resnet18_CF-k_8.pth    | Ship           | 0.0 (4.453)            | 95.44 (0.171)          |
+| cifar10_resnet18_CF-k_9.pth    | Truck          | 0.0 (4.657)            | 95.59 (0.167)          |
+
 
 ---
 
-## Notes
-- The **Top-1 Accuracy** metric represents the percentage of correctly classified samples from the CIFAR-10 test set.
-- The excluded class refers to the class omitted during model training to evaluate its effect on accuracy.
-- Results for additional models are pending computation.
+### Notes
+
+1. **Forget Class Accuracy and Loss**:
+   - Across all excluded classes, the forget class accuracy is consistently `0.0`, demonstrating the effectiveness of the **CF-k** method in completely excluding the target classes.
+   - The forget class loss varies slightly, ranging from `4.348` ("Frog") to `5.098` ("Cat"), suggesting that some classes might be slightly more challenging to suppress completely in terms of loss.
+
+2. **Retain Class Accuracy and Loss**:
+   - The retain class accuracy is consistently high across all excluded classes, ranging from `81.22%` ("Airplane") to `96.54%` ("Cat"). This indicates that the method effectively preserves performance on the remaining classes.
+   - Retain class loss is minimal, with the lowest being `0.122` for "Cat" and the highest being `0.578` for "Airplane." This suggests that the model maintains stable performance with minimal degradation on the retained classes.
+
+3. **Class-Specific Observations**:
+   - "Cat" shows the highest retain class accuracy (96.54%) and the lowest retain class loss (0.122), making it the least affected by the exclusion of other classes.
+   - "Airplane" exhibits the lowest retain class accuracy (81.22%) and the highest retain class loss (0.578), indicating a potential trade-off in preserving performance for this class.
+   - Variations in retain class accuracy and forget class loss across different excluded classes highlight the potential influence of class-specific features on model performance.
 
 ---
 
-## Conclusion
-This report highlights the results of applying the CF-k algorithm for inexact unlearning on the CIFAR-10 dataset. The CF-k algorithm enables efficient and systematic unlearning of specific classes, providing insights into model behavior under class removal constraints. Further experiments will help validate its effectiveness across various scenarios.
+### Conclusion
+
+The results illustrate that the **CF-k method** is highly effective in achieving class-specific exclusion while maintaining strong performance on the retained classes. However, minor variations in performance across classes reveal opportunities for further refinement:
+
+- **Strengths**:
+  - The forget class accuracy remains at `0.0` for all excluded classes, achieving complete suppression of the target classes.
+  - Retain class accuracy is high across the board, with most classes exceeding `95%`, showing the robustness of the method in retaining knowledge.
+
+- **Weaknesses**:
+  - "Airplane" has noticeably lower retain class accuracy (81.22%) and higher retain class loss (0.578), indicating that certain classes may be more challenging to balance during the exclusion process.
+  - Slight variations in forget class loss suggest that the suppression process may not be uniformly effective across all classes.
+
+- **Future Work**:
+  - Investigate why certain classes, such as "Airplane," are more impacted in terms of retain class accuracy and loss. Class-specific characteristics or relationships with other classes might influence this outcome.
+  - Explore adaptive mechanisms to optimize the trade-off between exclusion and retention for more balanced performance across all classes.
+  - Conduct additional experiments to determine if similar patterns emerge in other datasets or architectures, which could validate the generalizability of the method.
+