The Industrial Internet of Things (IIoT) leverages Federated Learning (FL) for distributed model training while preserving data privacy, and meta-computing enhances FL by optimizing and integrating distributed computi...
详细信息
Ag and Cu based nanostructures serve as advanced functional materials for biomedical applications, due to their unique properties. Here, we proposed a novel neurotransmitter biosensing method based on Ag-Cu composite ...
详细信息
Few-shot inductive link prediction on knowledge graphs (KGs) aims to predict missing links for unseen entities with few-shot links observed. Previous methods are limited to transductive scenarios, where entities exist...
详细信息
The blockchain technology has attracted attention due to its characteristics of anonymity, openness, decentralization, traceability, and tamper-resistance. However, with the development of the blockchain industry, var...
详细信息
Unsupervised learning utilizes unlabeled data to alleviate the reliance on large amounts of labeled data, and it has made great progress in time series anomaly detection. However, there are still some thorny issues un...
详细信息
—Intelligent reflecting surfaces (IRSs), active and/or passive, can be densely deployed in complex environments to significantly enhance wireless network coverage for both wireless information transfer (WIT) and wire...
详细信息
High-quality LiDAR point cloud (LPC) coding is essential for efficiently transmitting and storing the vast amounts of data required for accurate 3D environmental representation. The Octree-based entropy coding framewo...
详细信息
In this paper, we consider a real-world scenario where a model that is trained on pre-defined classes continually encounters unlabeled data that contains both known and novel classes. The goal is to continually discov...
In this paper, we consider a real-world scenario where a model that is trained on pre-defined classes continually encounters unlabeled data that contains both known and novel classes. The goal is to continually discover novel classes while maintaining the performance in known classes. We name the setting Continual Generalized Category Discovery (C-GCD). Existing methods for novel class discovery cannot directly handle the C-GCD setting due to some unrealistic assumptions, such as the unlabeled data only containing novel classes. Furthermore, they fail to discover novel classes in a continual fashion. In this work, we lift all these assumptions and propose an approach, called MetaGCD, to learn how to incrementally discover with less forgetting. Our proposed method uses a meta-learning framework and leverages the offline labeled data to simulate the testing incremental learning process. A meta-objective is defined to revolve around two conflicting learning objectives to achieve novel class discovery without forgetting. Furthermore, a soft neighborhood-based contrastive network is proposed to discriminate uncorrelated images while attracting correlated images. We build strong baselines and conduct extensive experiments on three widely used benchmarks to demonstrate the superiority of our method.
How to effectively compress mechanical signals so that they can support remote and real-time health monitoring is a hot issue in the context of intelligent manufacturing. Therefore, this paper presents a novel mechani...
详细信息
We introduce ZOOMER, a system deployed at Taobao, the largest e-commerce platform in China, for training and serving GNN-based recommendations over web-scale graphs. ZOOMER is designed for tackling two challenges pres...
详细信息
暂无评论