Related papers: Forward Once for All: Structural Parameterized Ada…

Most edge AI focuses on prediction tasks on resource-limited edge devices while the training is done at server machines. However, retraining or customizing a model is required at edge devices as the model is becoming outdated due to…

The rapid growth of data generated from Internet of Things (IoTs) such as smart phones and smart home devices presents new challenges to cloud computing in transferring, storing, and processing the data. With increasingly more powerful edge…

The trend towards the cloudification of the 3GPP LTE mobile network architecture and the emergence of federated cloud infrastructures call for alternative service delivery strategies for improved user experience and efficient resource…

Federated learning (FL) enables multiple clients to collaboratively train deep learning models while considering sensitive local datasets' privacy. However, adversaries can manipulate datasets and upload models by injecting triggers for…

Parameter-efficient fine-tuning (PEFT) has become increasingly important as foundation models continue to grow in both popularity and size. Adapter has been particularly well-received due to their potential for parameter reduction and…

With sequentially stacked self-attention, (optional) encoder-decoder attention, and feed-forward layers, Transformer achieves big success in natural language processing (NLP), and many variants have been proposed. Currently, almost all…

Making accurate recommendations for cold-start users has been a longstanding and critical challenge for recommender systems (RS). Cross-domain recommendations (CDR) offer a solution to tackle such a cold-start problem when there is no…

As industrial recommender systems enter a scaling-driven regime, Transformer architectures have become increasingly attractive for scaling models towards larger capacity and longer sequence. However, existing Transformer-based…

Federated learning (FL) is capable of performing large distributed machine learning tasks across multiple edge users by periodically aggregating trained local parameters. To address key challenges of enabling FL over a wireless fog-cloud…

In recommender systems, modeling user-item behaviors is essential for user representation learning. Existing sequential recommenders consider the sequential correlations between historically interacted items for capturing users' historical…

The increasingly stringent regulations on privacy protection have sparked interest in federated learning. As a distributed machine learning framework, it bridges isolated data islands by training a global model over devices while keeping…

The standardization of the sixth-generation (6G) has recently commenced to address the rapidly growing demands for enhanced wireless network services. Nevertheless, existing wireless systems, particularly at the physical layer waveform…

The pursuit of improved accuracy in recommender systems has led to the incorporation of user context. Context-aware recommender systems typically handle large amounts of data which must be uploaded and stored on the cloud, putting the…

Conventional federated learning (FL) trains one global model for a federation of clients with decentralized data, reducing the privacy risk of centralized training. However, the distribution shift across non-IID datasets, often poses a…

Over-the-air federated learning (OTA-FL) unifies communication and model aggregation by leveraging the inherent superposition property of the wireless medium. This strategy can enable scalable and bandwidth-efficient learning via…

As a promising distributed machine learning paradigm, Federated Learning (FL) enables all the involved devices to train a global model collaboratively without exposing their local data privacy. However, for non-IID scenarios, the…

Continual learning aims to avoid catastrophic forgetting and effectively leverage learned experiences to master new knowledge. Existing gradient projection approaches impose hard constraints on the optimization space for new tasks to…

This paper proposes a composable fine-tuning method that integrates graph structural priors with modular adapters to address the high computational cost and structural instability faced by large-scale pre-trained models in multi-task…

In today's typical industrial environments, the computation of the data distribution schedules is highly centralised. Typically, a central entity configures the data forwarding paths so as to guarantee low delivery delays between data…

Backdoor detection is currently the mainstream defense against backdoor attacks in federated learning (FL), where a small number of malicious clients can upload poisoned updates to compromise the federated global model. Existing backdoor…