English
Related papers

Related papers: Causality-Induced Positional Encoding for Transfor…

200 papers

Unsupervised pre-training on vast amounts of graph data is critical in real-world applications wherein labeled data is limited, such as molecule properties prediction or materials science. Existing approaches pre-train models for specific…

Machine Learning · Computer Science 2024-10-01 Viet Anh Nguyen , Nhat Khang Ngo , Truong Son Hy

We establish conditions under which latent causal graphs are nonparametrically identifiable and can be reconstructed from unknown interventions in the latent space. Our primary focus is the identification of the latent structure in…

Machine Learning · Statistics 2023-11-06 Yibo Jiang , Bryon Aragam

Discovery of causal relationships from observational data is an important problem in many areas. Several recent results have established the identifiability of causal DAGs with non-Gaussian and/or nonlinear structural equation models…

Machine Learning · Statistics 2020-12-15 Bingling Wang , Qing Zhou

Causal discovery aims to infer causal relationships among variables from observational data, typically represented by a directed acyclic graph (DAG). Most existing methods assume independent and identically distributed observations, an…

Methodology · Statistics 2026-03-27 Alex Chen , Qing Zhou

Learning the structure of a causal graphical model using both observational and interventional data is a fundamental problem in many scientific fields. A promising direction is continuous optimization for score-based methods, which,…

Machine Learning · Computer Science 2022-02-28 Phillip Lippe , Taco Cohen , Efstratios Gavves

Transformers have exhibited exceptional capabilities in sequence modeling tasks, leveraging self-attention and in-context learning. Critical to this success are induction heads, attention circuits that enable copying tokens based on their…

Machine Learning · Computer Science 2025-09-11 Francesco D'Angelo , Francesco Croce , Nicolas Flammarion

Recent studies have revealed various manifestations of position bias in transformer architectures, from the "lost-in-the-middle" phenomenon to attention sinks, yet a comprehensive theoretical understanding of how attention masks and…

Machine Learning · Computer Science 2025-08-12 Xinyi Wu , Yifei Wang , Stefanie Jegelka , Ali Jadbabaie

Capturing the underlying structural causal relations represented by Directed Acyclic Graphs (DAGs) has been a fundamental task in various AI disciplines. Causal DAG learning via the continuous optimization framework has recently achieved…

Machine Learning · Computer Science 2024-06-11 Naiyu Yin , Tian Gao , Yue Yu , Qiang Ji

We present a novel form of Fourier analysis, and associated signal processing concepts, for signals (or data) indexed by edge-weighted directed acyclic graphs (DAGs). This means that our Fourier basis yields an eigendecomposition of a…

Signal Processing · Electrical Eng. & Systems 2025-01-29 Bastian Seifert , Chris Wendler , Markus Püschel

Transformers are increasingly employed for graph data, demonstrating competitive performance in diverse tasks. To incorporate graph information into these models, it is essential to enhance node and edge features with positional encodings.…

Learning the causal structure that underlies data is a crucial step towards robust real-world decision making. The majority of existing work in causal inference focuses on determining a single directed acyclic graph (DAG) or a Markov…

Machine Learning · Computer Science 2021-06-15 Yashas Annadani , Jonas Rothfuss , Alexandre Lacoste , Nino Scherrer , Anirudh Goyal , Yoshua Bengio , Stefan Bauer

Graph structured data are abundant in the real world. Among different graph types, directed acyclic graphs (DAGs) are of particular interest to machine learning researchers, as many machine learning models are realized as computations on…

Machine Learning · Computer Science 2019-10-30 Muhan Zhang , Shali Jiang , Zhicheng Cui , Roman Garnett , Yixin Chen

Causal discovery from observational data is an important tool in many branches of science. Under certain assumptions it allows scientists to explain phenomena, predict, and make decisions. In the large sample limit, sound and complete…

Machine Learning · Statistics 2021-07-13 Shami Nisimov , Yaniv Gurwicz , Raanan Y. Rohekar , Gal Novik

Causal inference with observational data critically relies on untestable and extra-statistical assumptions that have (sometimes) testable implications. Well-known sets of assumptions that are sufficient to justify the causal interpretation…

Methodology · Statistics 2024-02-20 Pablo Geraldo Bastías

Learning directed acyclic graph (DAG) that describes the causality of observed data is a very challenging but important task. Due to the limited quantity and quality of observed data, and non-identifiability of causal graph, it is almost…

Machine Learning · Computer Science 2022-11-23 Dezhi Yang , Guoxian Yu , Jun Wang , Zhengtian Wu , Maozu Guo

Causal structures for observational survival data provide crucial information regarding the relationships between covariates and time-to-event. We derive motivation from the information theoretic source coding argument, and show that…

Machine Learning · Computer Science 2021-11-03 Ansh Kumar Sharma , Rahul Kukreja , Ranjitha Prasad , Shilpa Rao

Leveraging labelled data from multiple domains to enable prediction in another domain without labels is a significant, yet challenging problem. To address this problem, we introduce the framework DAPDAG (\textbf{D}omain \textbf{A}daptation…

Machine Learning · Computer Science 2022-08-03 Yanke Li , Hatt Tobias , Ioana Bica , Mihaela van der Schaar

Since self-attention layers in Transformers are permutation invariant by design, positional encodings must be explicitly incorporated to enable spatial understanding. However, fixed-size lookup tables used in traditional learnable position…

Machine Learning · Computer Science 2025-06-18 Huayang Li , Yahui Liu , Hongyu Sun , Deng Cai , Leyang Cui , Wei Bi , Peilin Zhao , Taro Watanabe

The Shapley Additive Global Importance (SAGE) value is a theoretically appealing interpretability method that fairly attributes global importance to a model's features. However, its exact calculation requires the computation of the…

Machine Learning · Statistics 2023-04-07 Christoph Luther , Gunnar König , Moritz Grosse-Wentrup

In multivariate time series analysis, understanding the underlying causal relationships among variables is often of interest for various applications. Directed acyclic graphs (DAGs) provide a powerful framework for representing causal…

Methodology · Statistics 2025-07-30 Arkaprava Roy , Anindya Roy , Subhashis Ghosal