paper-with-me

Papers

A Bayesian Framework for Information-Theoretic Probing

2021-09-08 · EMNLP 2021 11 · Tiago Pimentel, Ryan Cotterell

Pimentel et al. (2020) recently analysed probing from an information-theoretic perspective. They argue that probing should be seen as approximating a mutual information. This led to the rather unintuitive conclusion that representations encode exactly the same information about a target task as the original sentences. The mutual information, however, assumes the true probability distribution of a pair of random variables is known, leading to unintuitive results in settings where it is not. This paper proposes a new framework to measure what we term Bayesian mutual information, which analyses information from the perspective of Bayesian agents -- allowing for more intuitive findings in scenarios with finite data. For instance, under Bayesian MI we have that data can add information, processing can help, and information can hurt, which makes it more intuitive for machine learning applications. Finally, we apply our framework to probing where we believe Bayesian mutual information naturally operationalises ease of extraction by explicitly limiting the available background knowledge to solve a task.

📄 PDF Abstract BibTeX arXiv:2109.03853

Code (1)

rycolab/bayesian-mi 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Probing as Quantifying Inductive Bias

2021-10-15 · ACL 2022 5 · Alexander Immer, Lucas Torroba Hennigen, Vincent Fortuin, Ryan Cotterell

Pre-trained contextual representations have led to dramatic performance improvements on a range of downstream tasks. Such performance improvements have motivated researchers to quantify and understand the linguistic info…

Bayesian InferenceInductive Bias

Large Language Models are Not Stable Recommender Systems

2023-12-25 · TianHui Ma, Yuan Cheng, HengShu Zhu, Hui Xiong

With the significant successes of large language models (LLMs) in many natural language processing tasks, there is growing interest among researchers in exploring LLMs for novel recommender systems. However, we have obse…

Recommendation Systems

Probing Graph Representations

2023-03-07 · Mohammad Sadegh Akhondzadeh, Vijay Lingam, Aleksandar Bojchevski

Today we have a good theoretical understanding of the representational power of Graph Neural Networks (GNNs). For example, their limitations have been characterized in relation to a hierarchy of Weisfeiler-Lehman (WL) is…

Diagnostic

Constrained Bayesian Active Learning of Interference Channels in Cognitive Radio Networks

2017-10-23 · Anestis Tsakmalis, Symeon Chatzinotas, Björn Ottersten

In this paper, a sequential probing method for interference constraint learning is proposed to allow a centralized Cognitive Radio Network (CRN) accessing the frequency band of a Primary User (PU) in an underlay cognitiv…

Active Learning

Active Bayesian Inference for Robust Control under Sensor False Data Injection Attacks

2026-04-13 · Axel Andersson, György Dán arxiv

We present a framework for bridging the gap between sensor attack detection and recovery in cyber-physical systems. The proposed framework models modern-day, complex perception pipelines as bipartite graphs, which combin…

Bayesian Inference