Research map / Label-efficient and robust learning / Domain adaptation and generalization
Multi-Level Domain Adaptation and Contrastive Domain Isolation with Bilinear Fusion for Patient Drug Response Prediction
Yuting Bai, Hanwen Lv, Wanwan Shi, Zhiyi Zou, Jiawei Luo
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add tissue-aware loss (ablation) | MACB-DRP · Patient drug response (TCGA, 9 drugs, 5-fold CV) | average score: 0.6182 -> 0.6786 | Improved |
| add adversarial loss (ablation) | MACB-DRP · Patient drug response (TCGA, 9 drugs, 5-fold CV) | average score: 0.6187 -> 0.6786 | Improved |
| add conditional domain alignment (CDAN) loss (ablation) | MACB-DRP · Patient drug response (TCGA, 9 drugs, 5-fold CV) | average score: 0.6633 -> 0.6786 | Improved |
| add bilinear fusion (ablation) | MACB-DRP · Patient drug response (TCGA, 9 drugs, 5-fold CV) | average score: 0.6631 -> 0.6786 | Improved |
| add bilinear fusion (ablation) | MACB-DRP · Patient drug response (TCGA, 9 drugs, 5-fold CV) | F1: 0.6201 -> 0.6519 | Improved |
| add contrastive anchoring loss (ablation) | MACB-DRP · Patient drug response (TCGA, 9 drugs, 5-fold CV) | average score: 0.6491 -> 0.6786 | Improved |
| add positive pairs to contrastive anchoring (ablation) | MACB-DRP · Patient drug response (TCGA, 9 drugs, 5-fold CV) | average score: 0.6711 -> 0.6786 | Improved |
| add negative pairs to contrastive anchoring (ablation) | MACB-DRP · Patient drug response (TCGA, 9 drugs, 5-fold CV) | average score: 0.6473 -> 0.6786 | Improved |
| set contrastive weight alpha above 0.1 (ablation) | MACB-DRP · Patient drug response (TCGA, 9 drugs, 5-fold CV) | AUC and F1 | Hurt |
| set contrastive weight alpha below 0.1 (ablation) | MACB-DRP · Patient drug response (TCGA, 9 drugs, 5-fold CV) | all metrics | Hurt |
| vary number of positive samples K from 1 to 15 (ablation) | MACB-DRP · Patient drug response (TCGA, 9 drugs, 5-fold CV) | average score: K = 7: 0.6786 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- WISER — WISER: Weak Supervision and Supervised Representation Learning to Improve Drug Response Prediction in Cancer (ICML 2024) · better on 3 of 4 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Knowledge-Guided Domain Adaptation Model for Transferring Drug Response Prediction from Cell Lines to Patients (AAAI 2025 · similarity 0.92)
- Learning Cross-Domain Representations for Transferable Drug Perturbations on Single-Cell Transcriptional Responses (AAAI 2025 · similarity 0.86)
- WISER: Weak Supervision and Supervised Representation Learning to Improve Drug Response Prediction in Cancer (ICML 2024 · similarity 0.86)
- ScreenShot: A Foundation Model for Few-Shot Combination Drug Screening (NeurIPS 2026 · similarity 0.85)
- Predicting Dose-Response Curves with Deep Neural Networks (ICML 2024 · similarity 0.84)
- Learning Identifiable Factorized Causal Representations of Cellular Responses (NeurIPS 2024 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
