Results 121 to 130 of about 15,576,316 (273)
Dynamic Graph Information Bottleneck
Proceedings of the ACM Web Conference 2024Dynamic Graphs widely exist in the real world, which carry complicated spatial and temporal feature patterns, challenging their representation learning. Dynamic Graph Neural Networks (DGNNs) have shown impressive predictive abilities by exploiting the intrinsic dynamics. However, DGNNs exhibit limited robustness, prone to adversarial attacks.
Haonan Yuan +4 more
openaire +3 more sources
Advanced Functional Materials, EarlyView.Sulfur fluoride exchange (SuFEx) is a powerful click platform, yet water‐compatible multifunctional linchpins remain elusive. Here, we report decagram‐scalable diazonium linchpins that enable rapid Pd‐catalyzed diversification and direct, catalyst‐free on‐DNA ligation in aqueous media.
Seok Ju Hong +5 more
wiley +1 more source
Copula models in machine learning [PDF]
, 2015 The introduction of copulas, which allow separating the dependence structure of a multivariate distribution from its marginal behaviour, was a major advance in dependence modelling.
Rey, Mélanie
core +1 more source
Nanoscale Spatial Tuning of Superconductivity in Cuprate Thin Films via Direct Laser Writing
Advanced Functional Materials, EarlyView.Maskless direct laser writing enables local control of oxygen stoichiometry in epitaxial YBCO thin films under ambient conditions. Sub‐micrometer grayscale patterns with tunable optical response and superconducting transport properties are achieved.
Irene Biancardi +11 more
wiley +1 more source
Advanced Functional Materials, EarlyView.A single‐step laser annealing strategy is presented for dual‐gate a‐IGZO TFTs. The steep thermal gradient induces graded oxygen doping in the channel and simultaneous WOx removal at the contacts, enabling concurrent interface and contact engineering.
Sihyeon Kwon +9 more
wiley +1 more source
Bottleneck-level analysis of conditional variables.
Bottleneck-level analysis of conditional variables.
Ning Zhang (23771) +2 more
core +1 more source
Advanced Functional Materials, EarlyView.A systematic review is conducted to assess the influence of electrode architecture across micro‐ to mesoscopic length scales on electron‐transfer pathways in electrocatalysis. We discuss the structure‐activity relationships in electrocatalytic applications, including resource recovery and environmental remediation, and provide cost‐effective, efficient
Manshu Zhao +6 more
wiley +1 more source
Elastic Information Bottleneck
, 2023 Information bottleneck is an information-theoretic principle of representation learning that aims to learn a maximally compressed representation that preserves as much information about labels as possible. Under this principle, two different methods have
Liu, Ao +3 more
core
Advanced Functional Materials, EarlyView.This Perspective highlights atom probe tomography as a powerful tool for understanding the atomic‐scale defect chemistry in HfO2‐based ferroelectrics. 3D mapping of dopants, point defects, and interface chemistry can provide new insight into defect‐driven mechanisms underpinning the ferroelectricity in the system and guide the design of more reliable ...
Kasper Hunnestad +3 more
wiley +1 more source
Conditional Information Bottleneck Clustering
, 2003 We present an extension of the well-known information bottleneck framework, called conditional information bottleneck, which takes negative relevance information into account by maximizing a conditional mutual information score. This general approach can
David Gondek, Thomas Hofmann
core +1 more source