Search Results

Graph Contrastive Learning (GCL) effectively mitigates label dependency, defining positive and negative pairs for node embeddings. Nevertheless, most GCL methods, including those considering communities, overlooking the simultaneous influence of ...

Display Omitted

• Defined dual influenced community strength by topology and node attributes to measure node cruciality.
• Developed graph data augmentation methods for attributes and edges based on node cruciality.
• Proposed multi-scale graph ...

Abnormal email bounces seriously disrupt user lives and company transactions. Proliferating security protocols and protection strategies have made email delivery increasingly complex. A natural question is how and why email delivery fails in the wild. ...

Cross-domain few-shot Learning (CDFSL) is proposed to first pre-train deep models on a source domain dataset where sufficient data is available, and then generalize models to target domains to learn from only limited data. However, the gap ...

Humans exhibit a remarkable ability to learn quickly from a limited number of labeled samples, a capability that starkly contrasts with that of current machine learning systems. Unsupervised Few-Shot Learning (U-FSL) seeks to bridge this divide by ...

Few-shot open-set recognition (FSOR) is a challenging task that requires a model to recognize known classes and identify unknown classes with limited labeled data. Existing approaches, particularly Negative-Prototype-Based methods, generate negative ...

Federated learning is a promising distributed training paradigm that effectively safeguards data privacy. However, it may involve significant communication costs, which hinders training efficiency. In this paper, we aim to enhance communication ...

This paper focuses on Federated Domain-Incremental Learning (FDIL) where each client continues to learn incremental tasks where their domain shifts from each other. We propose a novel adaptive knowledge matching-based personalized FDIL approach (...

Hybrid parallelism is popular in training large language models (LLMs). However, existing efforts have focused on optimizing individual strategies in hybrid parallelism, such as pipeline scheduling, device assignment, etc., which limits the ...$$

Federated Learning (FL) suffers from severe performance degradation due to the data heterogeneity among clients. Some existing work suggests that the fundamental reason is that data heterogeneity can cause local model drift, and therefore proposes to ...

In the domain of Graph Federated Learning (GFL), prevalent methods often focus on local client data, which can limit the understanding of broader global patterns and pose challenges with Non-IID (Non-Independent and Identically Distributed) issues ...

Due to the prevalence of scalping and the promotion of realname ticketing systems, user-oriented mobile ticket grabbing apps have become a popular pattern for scalpers. Compared with traditional scalper-oriented scalping, ticket grabbing apps pose ...

Few-shot class-incremental learning (FSCIL) aims to acquire knowledge from novel classes with limited samples while retaining information about base classes. Existing methods address catastrophic forgetting and overfitting by freezing the feature ...

Federated Learning (FL) is to allow multiple clients to collaboratively train a model while keeping their data locally. However, existing FL approaches typically assume that the data in each client is static and fixed, which cannot account for incremental ...

Few-shot class-incremental learning (FSCIL) is proposed to continually learn from novel classes with only a few samples after the (pre-)training on base classes with sufficient data. However, this remains a challenge. In contrast, humans can easily ...

Federated learning is a promising distributed machine learning paradigm that can effectively exploit large-scale data without exposing users' privacy. However, it may incur significant communication overhead, thereby potentially impairing the training ...

• Developed a domain ontology model for food live-streaming promotion. Utilizing international codes and industry constraints, this model categorizes and standardizes data, creating five event types and 18 event argument roles to enhance the ...

In the evolving landscape of food e-commerce live streaming, the profusion of textual data, marked by an excess of promotional vernacular and unstructured formats, presents a formidable challenge for event extraction. Addressing these hurdles, we ...

To protect user DNS privacy, four DNS over Encryption (DoE) protocols have been proposed, including DNS over TLS (DoT), DNS over HTTPS (DoH), DNS over QUIC (DoQ), and DNS over HTTP/3 (DoH3). Ensuring reachability stands as a prominent prerequisite for ...

Masked graph autoencoders have emerged as a powerful graph self-supervised learning method that has yet to be fully explored. In this paper, we unveil that the existing discrete edge masking and binary link reconstruction strategies are insufficient to ...

Audio data augmentation is widely adopted in automatic speech recognition (ASR) to alleviate the overfitting problem. However, noise-based data augmentation converts an over-fitting problem into an under-fitting problem which increases the ...

Few-shot intent classification and slot filling are important but challenging tasks due to the scarcity of finely labeled data. Therefore, current works first train a model on source domains with sufficiently labeled data, and then transfer the model to ...