按年被提到
20212021 · 1 次2026
大模型与语言模型›可解释性与表征研究·arXiv:2102.11107 · cs.LG

Towards Causal Representation Learning

Bernhard Schölkopf, Francesco Locatello, Stefan Bauer, Nan Rosemary Ke, Nal Kalchbrenner, Anirudh Goyal, Yoshua Bengio · 2021
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2021-03-03 · 最近 2022-04-26
2不同的人
2活跃月份
2讨论串
75被引(OpenAlex)
arXiv 摘要(候选层不写导读)

The two fields of machine learning and graphical causality arose and developed separately. However, there is now cross-pollination and increasing interest in both fields to benefit from the advances of the other. In the present paper, we review fundamental concepts of causal inference and relate them to crucial open problems of machine learning, including transfer and generalization, thereby assaying how causality can contribute to modern machine learning research. This also applies in the opposite direction: we note that most work in causality starts from the premise that the causal variables are given. A central problem for AI and causality is, thus, causal representation learning, the discovery of high-level causal variables from low-level observations. Finally, we delineate some implications of causality for machine learning and propose key research areas at the intersection of both communities.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论bradyneal · 2022-04

“Causal representation learning by far (e.g. learning the things that can influence each other, given an image)! This is the topic that Yoshua Bengio gave a guest talk on in the course. Here's the big paper he and others wrote on the topic (after the course): https://arxiv.org/abs/2102.11107”

Introduction to Causal Inference (Causal AI)原评论 ↗
被提交为 story · 1 次