The geometry of feature space in deep learning models: a holistic perspective and comprehensive review
M Lee - Mathematics, 2023 - mdpi.com
As the field of deep learning experiences a meteoric rise, the urgency to decipher the
complex geometric properties of feature spaces, which underlie the effectiveness of diverse …
complex geometric properties of feature spaces, which underlie the effectiveness of diverse …
Exploring data geometry for continual learning
Continual learning aims to efficiently learn from a non-stationary stream of data while
avoiding forgetting the knowledge of old data. In many practical applications, data complies …
avoiding forgetting the knowledge of old data. In many practical applications, data complies …
Invisible Black-Box Backdoor Attack against Deep Cross-Modal Hashing Retrieval
Deep cross-modal hashing has promoted the field of multi-modal retrieval due to its
excellent efficiency and storage, but its vulnerability to backdoor attacks is rarely studied …
excellent efficiency and storage, but its vulnerability to backdoor attacks is rarely studied …
Enhancing Dynamic Image Advertising with Vision-Language Pre-training
In the multimedia era, image becomes an effective medium in search advertising. Dynamic
Image Advertising (DIA), a system that matches queries with appropriate ad images and …
Image Advertising (DIA), a system that matches queries with appropriate ad images and …
Multi-space interaction learning for disentangled knowledge-aware recommendation
K Li, Y Zhang, J Zhu, X Li, X Wang - Expert Systems with Applications, 2024 - Elsevier
Abstract Knowledge graphs are becoming increasingly valuable as auxiliary information in
current recommendation systems. User-item interaction modeling (within user-item …
current recommendation systems. User-item interaction modeling (within user-item …
ESMC: Entire Space Multi-Task Model for Post-Click Conversion Rate via Parameter Constraint
Z Jiang, B Zeng, H Feng, J Liu, J Fan, J Zhang… - arXiv preprint arXiv …, 2023 - arxiv.org
Large-scale online recommender system spreads all over the Internet being in charge of two
basic tasks: Click-Through Rate (CTR) and Post-Click Conversion Rate (CVR) estimations …
basic tasks: Click-Through Rate (CTR) and Post-Click Conversion Rate (CVR) estimations …
Improving Heterogeneous Graph Learning with Weighted Mixed-Curvature Product Manifold
T Nguyen-Van, DD Le, TA Ta - arXiv preprint arXiv:2307.04514, 2023 - arxiv.org
In graph representation learning, it is important that the complex geometric structure of the
input graph, eg hidden relations among nodes, is well captured in embedding space …
input graph, eg hidden relations among nodes, is well captured in embedding space …