首页/论文/2003.09712

arXiv 2003.097122020-03-21cs.LGcs.AIstat.ML

Understanding the Power and Limitations of Teaching with Imperfect Knowledge

Max Planck Institute for Software Systems (MPI-SWS)（马克斯·普朗克软件系统研究所）；ETH Zurich（苏黎世联邦理工学院）；University of Chicago（芝加哥大学）

Rati Devidze, Farnam Mansouri, Luis Haug, Yuxin Chen, Adish Singla

英文摘要：

Machine teaching studies the interaction between a teacher and a student/learner where the teacher selects training examples for the learner to learn a specific task. The typical assumption is that the teacher has perfect knowledge of the task---this knowledge comprises knowing the desired learning target, having the exact task representation used by the learner, and knowing the parameters capturing the learning dynamics of the learner. Inspired by real-world applications of machine teaching in education, we consider the setting where teacher's knowledge is limited and noisy, and the key research question we study is the following: When does a teacher succeed or fail in effectively teaching a learner using its imperfect knowledge? We answer this question by showing connections to how imperfect knowledge affects the teacher's solution of the corresponding machine teaching problem when constructing optimal teaching sets. Our results have important implications for designing robust teaching algorithms for real-world applications.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Teaching Categories to Human Learners with Visual Explanations

California Institute of Technology（加州理工学院）

We study the problem of computer-assisted teaching with explanations. Conventional approaches for machine teaching typically only provide feedback at the instance level e.g., the category or label of the instance. However, it is intuitive that clear explanations from a knowledgeable teacher can significantly improve a student's ability to learn a new concept. To address these existing limitations, we propose a teaching framework that provides interpretable explanations as feedback and models how the learner incorporates this additional information. In the case of images, we show that we can au…

2018-02-20cs.CVcs.LGstat.ML

Algorithmic recourse under imperfect causal knowledge: a probabilistic approach

Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；Max Planck ETH Center for Learning Systems（马克斯·普朗克-ETH学习系统中心）；University of Cambridge（剑桥大学）；Saarland University（萨尔兰大学）

Recent work has discussed the limitations of counterfactual explanations to recommend actions for algorithmic recourse, and argued for the need of taking causal relationships between features into consideration. Unfortunately, in practice, the true underlying structural causal model is generally unknown. In this work, we first show that it is impossible to guarantee recourse without access to the true structural equations. To address this limitation, we propose two probabilistic approaches to select optimal actions that achieve recourse with high probability given limited causal knowledge (e.g…

2020-10-23cs.AIcs.LGstat.ML

不完美结构约束下的鲁棒因果发现

Robust Causal Discovery under Imperfect Structural Constraints

本文针对不完美结构约束下的因果发现问题，提出通过先验对齐与多任务多梯度优化协调知识与数据，提升线性和非线性场景下的鲁棒因果发现性能。

2025-11-10cs.AIcs.LGstat.ML

非参数迭代机器教学

Nonparametric Iterative Machine Teaching

Jilin University（吉林大学）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；University of Cambridge（剑桥大学）；A*STAR（新加坡科技研究局）；Hong Kong University of Science and Technology（香港科技大学）

本文提出非参数迭代机器教学 NIMT，将教学建模为函数空间优化，并给出随机与贪心算法及 ITD 界，实验验证其理论结果。

2023-06-06cs.AIcs.CVcs.LG

通过额外训练将特定科学知识注入大语言模型

Teaching Specific Scientific Knowledge into Large Language Models through Additional Training

Tokyo Institute of Technology（东京工业大学）；University of Tsukuba（筑波大学）；The University of Tokyo（东京大学）

本研究探索通过额外训练向Llama 2注入科学知识，采用文本增强、超参数优化等方法，用6.5万篇论文验证，实现部分知识嵌入并指明后续改进方向。

2023-12-18cs.AIcs.CLcs.LG

Teachable Reality: Prototyping Tangible Augmented Reality with Everyday Objects by Leveraging Interactive Machine Teaching

IIIT-Delhi（德里英迪拉甘地信息技术学院）；University of Calgary（卡尔加里大学）

This paper introduces Teachable Reality, an augmented reality (AR) prototyping tool for creating interactive tangible AR applications with arbitrary everyday objects. Teachable Reality leverages vision-based interactive machine teaching (e.g., Teachable Machine), which captures real-world interactions for AR prototyping. It identifies the user-defined tangible and gestural interactions using an on-demand computer vision model. Based on this, the user can easily create functional AR prototypes without programming, enabled by a trigger-action authoring interface. Therefore, our approach allows t…

2023-02-21cs.CVcs.HCcs.LG

更多相关论文收起更多论文

Intuitiveness in Active Teaching

Bielefeld University（比勒费尔德大学）；Honda Research Institute Europe（本田欧洲研究院）

While Machine learning gives rise to astonishing results in automated systems, it is usually at the cost of large data requirements. This makes many successful algorithms from machine learning unsuitable for human-machine interaction, where the machine must learn from a small number of training samples that can be provided by a user within a reasonable time frame. Fortunately, the user can tailor the training data they create to be as useful as possible, severely limiting its necessary size -- as long as they know about the machine's requirements and limitations. Of course, acquiring this know…

2021-09-29cs.HCcs.LG

AdvFunMatch：当一致性教学遇上对抗鲁棒性

AdvFunMatch: When Consistent Teaching Meets Adversarial Robustness

Xidian University（西安电子科技大学）

本文提出 AdvFunMatch 方法，通过在一致性教学框架下对 $\ell_p$-范数球内最坏情况样本进行函数匹配，实现对抗鲁棒性从教师模型到学生模型的有效迁移，同时保持高干净准确率。

2023-05-25cs.CVcs.LG

Astute RAG：克服大型语言模型的不完美检索增强与知识冲突

Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models

Google Cloud AI Research（谷歌云人工智能研究）；University of Southern California（南加州大学）

针对不完美检索导致的错误传播与知识冲突问题，提出Astute RAG方法，通过自适应提取内部知识、迭代整合内外知识并依据可靠性生成答案，显著提升了LLM在最坏情况下的鲁棒性与可信度。

2025-05-31cs.AIcs.CLcs.LG

Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentation

VoxelCloud, Inc.（体素云公司）

The medical imaging literature has witnessed remarkable progress in high-performing segmentation models based on convolutional neural networks. Despite the new performance highs, the recent advanced segmentation models still require large, representative, and high quality annotated datasets. However, rarely do we have a perfect training dataset, particularly in the field of medical imaging, where data and annotations are both expensive to acquire. Recently, a large body of research has studied the problem of medical image segmentation with imperfect datasets, tackling two major dataset limitat…

2020-02-12cs.CVcs.LGeess.IV

Improving mathematical questioning in teacher training

University of Virginia（弗吉尼亚大学）；James Madison University（詹姆斯麦迪逊大学）

High-fidelity, AI-based simulated classroom systems enable teachers to rehearse effective teaching strategies. However, dialogue-oriented open-ended conversations such as teaching a student about scale factors can be difficult to model. This paper builds a text-based interactive conversational agent to help teachers practice mathematical questioning skills based on the well-known Instructional Quality Assessment. We take a human-centered approach to designing our system, relying on advances in deep learning, uncertainty quantification, and natural language processing while acknowledging the li…

2021-12-06cs.AIcs.HCcs.LG

ViTs：教机器像人类专家一样识别时间序列异常

ViTs: Teaching Machines to See Time Series Anomalies Like Human Experts

Computer Network Information Center, Chinese Academy of Sciences（中国科学院计算机网络信息中心）；Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences（中国科学院大学杭州先进研究所）；Tsinghua University（清华大学）

针对时间序列异常检测模型泛化性差、输入长度受限的问题，提出基于视觉语言模型的ViTs框架，通过图像化转换和三阶段训练实现任意长序列零样本异常检测，性能显著提升。

2025-10-06cs.LG