Teaching

The first edition of the project on XAI.

Meetings

1. 10.04 (Thursday)

   • organisational matters

   • assignment of presentation topics

   • brief introduction to XAI

2. 14.04 (Monday)

   • presentation: Saliency Maps - Vanilla Gradient  & GradCAM & DeepLift (by Mikołaj H.)

3. 24.04  (Thursday)

   • Project - Topic Presentations

4. 28.04  (Monday)

   • presentation: Variable Importance (Linear Regression, Random Forest, xGBoost) (by Emre B., Jakub M.)

   • presentation: Feature Visualization, Importance & Sensitivity Analysis for Images (by Jan B., Dominik B.)

5. 08.05 (Thursday)

   • presentation: Shapley-Values & SHAP (by Dawid K.)

   • prepare a PoC for your project (basic analysis of the data, simple preprocessing, build a black-box model, evaluate the model, add any explanation method to it, make a short summary of the results)

6. 12.05  (Monday)

   • presentation: LIME (by Agnieszka G, Zuzanna K.)

7. 15.05 (Thursday)

   • project chechpoint

8. 19.05  (Monday)

   • Explaining GANs (by Emre B., Jakub M.)

9. 26.05  (Monday)

   • Project - Milestone Presentations

10. 29.05 (Thursday)

    • Circuits in Transformers (by Mikołaj H.)

11. 02.06  (Monday)

    • Explaining BERT (by Dawid K.)

12. 05.06 (Thursday)

    • Explaining RS (by Natalia P.)

13. 09.06  (Monday)

    • Explaining Bounding Boxes (by Agnieszka G., Zuzanna K., Dominik B.) presentation on 5:00 p.m. (project updates at 4:30 p.m.)

14. 12.06 (Thursday)

    • Towards Monosemanticity: Decomposing Language Models With Dictionary Learning (by Jan B.) 

15. 16.06  (Monday)

    • Project - Final Presentations

Materials

1. Basic Literature:

   • https://www.sciencedirect.com/science/article/pii/S1566253523001148

   • https://ema.drwhy.ai/

   • https://christophm.github.io/interpretable-ml-book/ 

2. Advanced Literature Reviews:

   • https://xainlp2020.github.io/xainlp/table

   • https://github.com/hbaniecki/adversarial-explainable-ai

   • https://github.com/SinaMohseni/Awesome-XAI-Evaluation

   • https://github.com/wangyongjie-ntu/Awesome-explainable-AI

   • https://github.com/pbiecek/xai_resources

   • https://github.com/lopusz/awesome-interpretable-machine-learning

   • https://github.com/rehmanzafar/xai-iml-sota

   • https://github.com/kevinmcareavey/chai-xai

   • https://github.com/feifeife/All-about-XAI

   • https://github.com/samzabdiel/XAI

   • https://github.com/AstraZeneca/awesome-explainable-graph-reasoning

   • https://github.com/anguyen8/XAI-papers

   • https://github.com/JHoelli/Awesome-Time-Series-Explainability?tab=readme-ov-file

3. Advanced Literature - selected papers:

   • Images:

     • https://papers.nips.cc/paper_files/paper/2019/hash/adf7ee2dcf142b0e11888e72b43fcb75-Abstract.html

     • https://arxiv.org/abs/2011.02863

     • https://arxiv.org/abs/2012.02046

     • https://dl.acm.org/doi/10.1145/3580305.3599290 

     • https://arxiv.org/abs/2110.15355

     • https://arxiv.org/abs/2108.11761

     • https://proceedings.neurips.cc/paper_files/paper/2022/hash/025f7165a452e7d0b57f1397fed3b0fd-Abstract-Conference.html

     • https://arxiv.org/abs/2208.03608

     • https://openaccess.thecvf.com/content/ICCV2021/html/Lee_LFI-CAM_Learning_Feature_Importance_for_Better_Visual_Explanation_ICCV_2021_paper.html

   • Tabular Data:

     • https://github.com/peymanrasouli/EXPLAN

     • https://arxiv.org/abs/1911.02042

     • https://arxiv.org/abs/1909.09369

     • https://arxiv.org/abs/1905.04610

     • https://dl.acm.org/doi/abs/10.1145/3412815.3416893

     • https://arxiv.org/abs/2202.00858

     • https://arxiv.org/abs/2104.02297

   • Graph-based Models:

     • https://arxiv.org/abs/2006.02587

     • https://arxiv.org/abs/2203.15209

     • https://arxiv.org/abs/1903.03894

     • https://proceedings.neurips.cc/paper_files/paper/2022/hash/a69d7f3a1340d55c720e572742439eaf-Abstract-Conference.html

     • https://arxiv.org/abs/2102.03322

   • NLP & LLMs:

     • https://arxiv.org/pdf/2010.00577

     • https://arxiv.org/abs/2202.07304

     • https://openreview.net/forum?id=H1z-PsR5KX

     • https://arxiv.org/abs/2010.02695

     • https://arxiv.org/abs/2212.10534

     • https://arxiv.org/abs/1906.02715

   • Audio:

     • https://openreview.net/pdf?id=FhuM-kk8Pbk

   • Temporal (Sequential, RS, Time Series):

     • https://arxiv.org/abs/2107.02776

     • https://dl.acm.org/doi/10.1145/3292500.3330989

     • https://arxiv.org/abs/2408.03636 

     • https://proceedings.mlr.press/v151/sivill22a.html

     • https://arxiv.org/abs/2003.02821

     • https://www.bu.edu/peaclab/files/2021/05/CoMTE___ICAPAI.pdf

     • https://arxiv.org/abs/2106.05303

     • https://arxiv.org/abs/2009.04796

2025-04-25 Lecture (Recommender Systems based on Matrix Factorization): https://drive.google.com/file/d/1Xx1yLUYeom6Coh6cuLnEkp2Xq-SpWvs5/view?usp=sharing

All information can be found at https://ii.uni.wroc.pl/~lipinski/lectureADM2025.html

Practical labs supporting the lecture on Machine Learning.

Time:

• Group 1:  Thursday,  14:15 - 16:00, room 139 

• Group 2:  Tuesday, 10:15 - 12:00, room 105

Announcements:

• Additional rules for our group: https://docs.google.com/document/d/1DnATA9u9_r2swM7pXu589DmM5FxxCzl_rLgTrbmiFwY/edit?usp=sharing 

• Project topic presentation: 17/19.12.2024

• Project milestone presentation: 14/16.01.2025

Classes:

1. Week 1 (3 & 8.10)

• ml_uwr_23/Assignments/Assignment1.ipynb at master · marekpiotradamczyk/ml_uwr_23 · GitHub -- first list may be similar 

• https://miro.com/app/board/uXjVLXHI3j0=/?share_link_id=206195427182 -- compressed notes from first classes

2. Week 2 (10 & 15.10)

• https://github.com/klaudiabalcer/demos/blob/main/notebooks/EDA.ipynb (data linked in the notebook)

3. Week 3 ()

4. Week 4

5. Week 5 (12 & 14.10)

   • https://www.kaggle.com/datasets/hellbuoy/car-price-prediction/data

   • https://github.com/klaudiabalcer/demos/blob/main/notebooks/linear_regression.ipynb

Example Project Topics:

• [TAKEN] Binary Classification for Credit Card Fraud Detection
  https://www.kaggle.com/datasets/mlg-ulb/creditcardfraud
  https://archive.ics.uci.edu/dataset/144/statlog+german+credit+data

• Community Detection with Spectral Clustering in e-commerce:
  https://paperswithcode.com/task/community-detection
  https://www.kaggle.com/datasets/lokeshparab/amazon-products-dataset

• Matrix Factorization for Movie Recommender Systems:
  https://paperswithcode.com/dataset/movielens,
  https://github.com/gbolmier/funk-svd, https://surpriselib.com/
  comparison to a neural approach like https://arxiv.org/abs/2302.08191

Also held in 2023/24.

Practical labs supporting the lecture on Advanced Python Course (2023/24).