Summary of Collaborative Cognitive Diagnosis with Disentangled Representation Learning For Learner Modeling, by Weibo Gao et al.
Collaborative Cognitive Diagnosis with Disentangled Representation Learning for Learner Modeling
by Weibo Gao, Qi Liu, Linan Yue, Fangzhou Yao, Hao Wang, Yin Gu, Zheng Zhang
First submitted to arxiv on: 4 Nov 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 The paper investigates how learners’ collaborative signals can be used to diagnose their cognitive states, specifically knowledge proficiency, in the context of intelligent education. The authors aim to develop a model that can simultaneously capture both collaborative and disentangled cognitive states, which is essential for explainability and controllability in learner Cognitive Diagnosis (CD). To address this challenge, they propose Coral, a Collaborative cognitive diagnosis model with disentangled representation learning. Coral first disentangles learners’ initial states using a state encoder, then captures collaborative signals through a meticulously designed procedure that constructs a collaborative graph of learners. The authors demonstrate the superior performance of Coral in experiments across several real-world datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper explores how people learn together and how we can use this information to understand what each person knows and doesn’t know. It’s like trying to figure out why a group of friends might be good at solving puzzles if they work together, but not when they’re working alone. The authors want to develop a system that can help us understand this connection between people and their learning abilities. They propose a new model called Coral that looks at both how individuals learn and how they work together to solve problems. By using this information, Coral can identify what each person knows and doesn’t know, which is important for making education more effective. |
Keywords
» Artificial intelligence » Encoder » Representation learning
