One crucial objective of multi-task learning is to align distributions across tasks so that the information between them can be transferred and shared. However, existing approaches only focused on matching the marginal feature distribution while ignoring the semantic information, which may hinder the learning performance. To address this issue, we propose to leverage the label information in multi-task learning by exploring the semantic conditional relations among tasks. We first theoretically analyze the generalization bound of multi-task learning based on the notion of Jensen-Shannon divergence, which provides new insights into the value of label information in multi-task learning. Our analysis also leads to a concrete algorithm that jointly matches the semantic distribution and controls label distribution divergence. To confirm the effectiveness of the proposed method, we first compare the algorithm with several baselines on some benchmarks and then test the algorithms under label space shift conditions. Empirical results demonstrate that the proposed method could outperform most baselines and achieve state-of-the-art performance, particularly showing the benefits under the label shift conditions.
Knowledge-Aided Semantic Communication Leveraging Probabilistic Graphical Modeling
Polytechnic Institute, Zhejiang University（浙江大学理工学院）；College of Information Science and Electronic Engineering, Zhejiang University（浙江大学信息科学与工程学院）；Jinhua Institute of Zhejiang University（浙江大学金华研究院）
Leveraging Distributional Semantics for Multi-Label Learning
IIT Kanpur（印度理工学院坎普尔分校）；Microsoft Research（微软研究院）
我们提出了一种新的和可扩展的标签嵌入框架，用于大规模的多标签学习a. k. aExMLDS（使用分布式语义的极端多标签学习）。我们的方法从分布式语义中汲取灵感，特别是跳过革兰氏阴性采样（SGNS）方法，广泛用于学习自然语言处理任务的词嵌入。学习这样的嵌入可以简化为某种矩阵分解。我们的方法是新颖的，因为它突出了用于多标签学习的标签嵌入方法和通常用于学习文本数据表示的段落/文档嵌入方法之间的有趣联系。该框架也可以很容易地扩展到包含辅助信息，如标签-标签相关性;这是至关重要的，特别是当训练数据中有很多缺失的标签时。我们通过在各种基准数据集上进行的大量实验证明了我们方法的有效性，并表明与几种基线和最先进的大规模多标签学习方法相比，所提出的学习方法表现良好。为了促进端到端的学习，我们开发了一个联合学习算法，可以学习嵌入以及回归模型，预测这些嵌入给定的输入功能，通过有效的基于梯度的方法。
SiHGNN: Leveraging Properties of Semantic Graphs for Efficient HGNN Acceleration
State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所 国家处理器重点实验室）；University of Chinese Academy of Sciences（中国科学院大学）；Faculty of Computility Microelectronics, Shenzhen University of Advanced Technology（深圳先进技术学院 计算微电子学院）
Temporal Sparse Autoencoders: Leveraging the Sequential Nature of Language for Interpretability
Harvard School of Engineering and Applied Science（哈佛工程与应用科学学院）；Kempner Institute for the Study of Natural & Artificial Intelligence（自然与人工智能研究学院）；Harvard Business School（哈佛商学院）
Trinity: Unifying Class-Agnostic Terrain and Semantic Segmentation for Unstructured Outdoor Environments by Leveraging Synthetic Data
Institute of Robotics and Mechatronics, German Aerospace Center (DLR)（机器人与机电系统研究所，德国航空航天中心（DLR））；Federal Institute of Technology Zurich (ETH Zurich)（苏黎世联邦理工学院（ETH Zurich））；Robotics and AI Institute (RAI)（机器人与人工智能研究所（RAI））
Leveraging weak complementary labels to improve semantic segmentation of hepatocellular carcinoma and cholangiocarcinoma in H&E-stained slides
Technische Universität Berlin（柏林工业大学）；Aignostics GmbH（Aignostics 公司）；Charité Universitätsmedizin Berlin（柏林夏里特医学院）；Berlin Institute of Health at Charité – Universitätsmedizin Berlin（柏林健康研究所（夏里特医学院））；University Hospital Düsseldorf（杜塞尔多夫大学医院）；Ludwig-Maximilians-Universität München（慕尼黑大学）；German Cancer Research Center（德国癌症研究中心）
Leveraging Semantic Attribute Binding for Free-Lunch Color Control in Diffusion Models
Computer Vision Center, Spain（西班牙计算机视觉中心）；Universitat Autònoma de Barcelona（巴塞罗那自治大学）；Harbin Institute of Technology（哈尔滨工业大学）；City University of Hong Kong（香港城市大学）；Program of Computer Science, City University of Hong Kong (Dongguan)（香港城市大学（东莞）计算机科学项目）
An Attentive Dual-Encoder Framework Leveraging Multimodal Visual and Semantic Information for Automatic OSAHS Diagnosis
School of Electronic and Electrical Engineering, Shanghai University of Engineering Science（上海工程技术大学电子与电气工程学院）；INF Technology (shanghai) Co., Ltd.（INF科技（上海）有限公司）；Artificial Intelligence Innovation and Incubation Institute, Fudan University（复旦大学人工智能创新与孵化研究院）
Leveraging SO(3)-steerable convolutions for pose-robust semantic segmentation in 3D medical data
Support Center for Advanced Neuroimaging (SCAN), University Institute of Diagnostic and Interventional Neuroradiology, University of Bern, Inselspital, Bern University Hospital（高级神经影像支持中心（SCAN）、伯尔尼大学诊断与介入神经放射学研究所、伯尔尼大学、因塞尔斯皮塔尔医院、伯尔尼大学医院）；NVIDIA（英伟达）
