Search Results

Few-shot Learning (FSL) aims to learn and distinguish new categories from a scant number of available samples, presenting a significant challenge in the realm of deep learning. Recent researchers have sought to leverage the additional semantic or ...

• Previous Semantic-based few-shot methods focus on designing complex fusion modules, while ignoring the generalization capacity of language models.
• We propose a simple framework, which fully exploits the LM with learnable prompts.
• ...

Network slicing has been envisioned to play a crucial role in supporting various vehicular applications with diverse performance requirements in dynamic Vehicle-to-Everything (V2X) communications systems. However, time-varying Service Level Agreements (...

Clustering is a fundamental machine learning task, which aim at assigning instances into groups so that similar samples belong to the same cluster while dissimilar samples belong to different clusters. Shallow clustering methods usually assume that data ...

Collaborative Perception (CP) has shown great potential to achieve more holistic and reliable environmental perception in intelligent unmanned systems (IUSs). However, implementing CP still faces key challenges due to the characteristics of the CP task ...

Implicit feedback (e.g., user clicks) is widely used in building recommender systems (RS). However, the inherent notorious exposure bias significantly affects recommendation performance. Exposure bias refers a phenomenon that implicit feedback is ...

Graph Neural Networks (GNNs) have demonstrated remarkable success in graph node classification task. However, their performance heavily relies on the availability of high-quality labeled data, which can be time-consuming and labor-intensive to ...

In scenarios like privacy protection or large-scale data transmission, data-free knowledge distillation (DFKD) methods are proposed to learn Knowledge Distillation (KD) when data is not accessible. They generate pseudo samples by extracting the ...

In recommender systems, most graph-based methods focus on positive user feedback, while overlooking the valuable negative feedback. Integrating both positive and negative feedback to form a signed graph can lead to a more comprehensive understanding of ...

Blind and visually impaired (BVI) individuals encounter significant challenges in perceiving the visual content of movies. Audio descriptions (AD) are inserted into speech gaps to describe visual content and storyline for BVI individuals. However, the ...

With the capacity to capture high-order collaborative signals, Graph Neural Networks (GNNs) have emerged as powerful methods in Recommender Systems (RS). However, their efficacy often hinges on the assumption that training and testing data share the same ...

Predicting Click-Through Rate (CTR) in billion-scale recommender systems poses a long-standing challenge for Graph Neural Networks (GNNs) due to the overwhelming computational complexity involved in aggregating billions of neighbors. To tackle this, GNN-...

To improve the performance of multi-agent reinforcement learning under the constraint of wireless resources, we propose a message importance metric and design an importance-aware scheduling policy to effectively exchange messages. The key insight is ...

Nowadays, environmental issues have received increasing attention from experts. The main cause is the increase of carbon emissions in the atmosphere, so it is urgent to reduce carbon emissions. In order to establish the optimal pricing strategy as ...

Knowledge distillation, a technique recently gaining popularity for enhancing model generalization in Convolutional Neural Networks (CNNs), operates under the assumption that both teacher and student models are trained on identical data ...

• We propose an Online Adversarial Knowledge Distillation framework for GNNs.
• OAD trains a group of GNN models to capture structure updates in GNNs.
• OAD extracts both local and global knowledge in graph structured data.
• Extensive ...

Unsupervised Graph Domain Adaptation (UGDA) aims to transfer knowledge from a labelled source graph to an unlabeled target graph in order to address the distribution shifts between graph domains. Previous works have primarily focused on aligning data ...

Recurrent Neural Networks (RNNs) are useful in temporal sequence tasks. However, training RNNs involves dense matrix multiplications which require hardware that can support a large number of arithmetic operations and memory accesses. Implementing online ...

Edge-enabled Industrial Internet of Things (E-IIoT) has gained massive attention as a new type of IIoT for hosting emerging low-latency applications. However, due to device variations and complex communication environments, the edge servers and channel ...

Effectively leveraging objects and optical character recognition (OCR) tokens to reason out pivotal scene text is critical for the challenging Text-based Visual Question Answering (TextVQA) task. Graph-based models can effectively capture the semantic ...

Graph Neural Networks (GNNs) have emerged as the de facto standard for representation learning on graphs, owing to their ability to effectively integrate graph topology and node attributes. However, the inherent suboptimal nature of node connections, ...

Extracting users' interests from their behavior, particularly their 1-hop neighbors, has been shown to enhance Click-Through Rate (CTR) prediction performance. However, online recommender systems impose strict constraints on the inference time of CTR ...