Related papers: HAMUR: Hyper Adapter for Multi-Domain Recommendati…

A practical shortcoming of deep neural networks is their specialization to a single task and domain. While recent techniques in domain adaptation and multi-domain learning enable the learning of more domain-agnostic features, their success…

Unsupervised domain adaptation (UDA) with pre-trained language models (PrLM) has achieved promising results since these pre-trained models embed generic knowledge learned from various domains. However, fine-tuning all the parameters of the…

Most few-shot learning works rely on the same domain assumption between the base and the target tasks, hindering their practical applications. This paper proposes an adaptive transformer network (ADAPTER), a simple but effective solution…

Multimodal Large Language Models (MLLMs) have achieved success across various domains. However, their applicability tends to degrade when confronted with different types of data inputs, especially for MLLMs that have been fine-tuned for…

Cross-domain recommendation (CDR) methods are proposed to tackle the sparsity problem in click through rate (CTR) estimation. Existing CDR methods directly transfer knowledge from the source domains to the target domain and ignore the…

Parameter sharing, as an important technique in multi-agent systems, can effectively solve the scalability issue in large-scale agent problems. However, the effectiveness of parameter sharing largely depends on the environment setting. When…

Human Activity Recognition (HAR) has been a popular research field due to the widespread of devices with sensors and computational power (e.g., smartphones and smartwatches). Applications for HAR systems have been extensively researched in…

We study the problem of choosing algorithm hyper-parameters in unsupervised domain adaptation, i.e., with labeled data in a source domain and unlabeled data in a target domain, drawn from a different input distribution. We follow the…

Traditional neural networks (multi-layer perceptrons) have become an important tool in data science due to their success across a wide range of tasks. However, their performance is sometimes unsatisfactory, and they often require a large…

Recommender systems have been widely deployed in many real-world applications, but usually suffer from the long-standing user cold-start problem. As a promising way, Cross-Domain Recommendation (CDR) has attracted a surge of interest, which…

Despite domain-adaptive object detectors based on CNN and transformers have made significant progress in cross-domain detection tasks, it is regrettable that domain adaptation for real-time transformer-based detectors has not yet been…

Multi-source unsupervised domain adaptation (MUDA) aims to transfer knowledge from related source domains to an unlabeled target domain. While recent MUDA methods have shown promising results, most focus on aligning the overall feature…

Recent advances in deep domain adaptation reveal that adversarial learning can be embedded into deep networks to learn transferable features that reduce distribution discrepancy between the source and target domains. Existing domain…

The current state-of-the art techniques for image segmentation are often based on U-Net architectures, a U-shaped encoder-decoder networks with skip connections. Despite the powerful performance, the architecture often does not perform well…

Minimizing the discrepancy of feature distributions between different domains is one of the most promising directions in unsupervised domain adaptation. From the perspective of distribution matching, most existing discrepancy-based methods…

We consider the problem of adapting a network trained on three-channel color images to a hyperspectral domain with a large number of channels. To this end, we propose domain adaptor networks that map the input to be compatible with a…

The goal of Online Domain Adaptation for semantic segmentation is to handle unforeseeable domain changes that occur during deployment, like sudden weather events. However, the high computational costs associated with brute-force adaptation…

Medication recommendation is a crucial task in healthcare, especially for patients with complex medical conditions. However, existing methods often struggle to effectively balance the reuse of historical medications with the introduction of…

The increasing popularity of deep learning models has created new opportunities for developing AI-based recommender systems. Designing recommender systems using deep neural networks requires careful architecture design, and further…

Deep neural networks (DNNs) offer plenty of challenges in executing efficient computation at edge nodes, primarily due to the huge hardware resource demands. The article proposes HYDRA, hybrid data multiplexing, and runtime layer…