Summary of Overcoming Uncertain Incompleteness For Robust Multimodal Sequential Diagnosis Prediction Via Curriculum Data Erasing Guided Knowledge Distillation, by Heejoon Koo
Overcoming Uncertain Incompleteness for Robust Multimodal Sequential Diagnosis Prediction via Curriculum Data Erasing Guided Knowledge Distillation
by Heejoon Koo
First submitted to arxiv on: 28 Jul 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper presents a novel framework called NECHO v2 to improve the predictive accuracy of patient diagnoses under uncertain missing visit sequences, a common challenge in clinical settings. The authors modify an existing framework, NECHO, to handle uncertain modality representation dominance and develop a systematic knowledge distillation approach using modified NECHO as both teacher and student. This includes contrastive and hierarchical distillation, transformer representation random distillation, and other distillations to align representations between teacher and student. Additionally, the authors propose curriculum learning guided random data erasing within sequences during training and distillation of the teacher to simulate missing visit information. The results show that NECHO v2 achieves robust superiority in multimodal sequential diagnosis prediction under both balanced and imbalanced incomplete settings on multimodal healthcare data. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps doctors make better predictions about patient diagnoses when they don’t have all the information. They create a new tool called NECHO v2 to improve accuracy. The authors make changes to an existing framework, NECHO, to handle uncertainty in patient data and develop a way to train a student model using the modified teacher model. This helps the student learn quickly from the teacher. The results show that NECHO v2 is better at making predictions when there’s missing information. |
Keywords
* Artificial intelligence * Curriculum learning * Distillation * Knowledge distillation * Student model * Teacher model * Transformer
