Related papers: Intelligent Elastic Feature Fading: Enabling Model…
Diffusion models have become a leading paradigm for image super-resolution (SR), but existing methods struggle to guarantee both the high-frequency perceptual quality and the low-frequency structural fidelity of generated images. Although…
The rapid advancement of large language models (LLMs) and the development of increasingly large and diverse evaluation benchmarks have introduced substantial computational challenges for model assessment. In this paper, we present EffiEval,…
Automated feature engineering (AutoFE) is the process of automatically building and selecting new features that help improve downstream predictive performance. While traditional feature engineering requires significant domain expertise and…
Federated Learning (FL) allows machine learning models to train locally on individual mobile devices, synchronizing model updates via a shared server. This approach safeguards user privacy; however, it also generates a heterogeneous…
Fine-tuning plays a crucial role in enabling pre-trained LLMs to evolve from general language comprehension to task-specific expertise. To preserve user data privacy, federated fine-tuning is often employed and has emerged as the de facto…
Recommender models are commonly used to suggest relevant items to a user for e-commerce and online advertisement-based applications. These models use massive embedding tables to store numerical representation of items' and users'…
Federated Learning (FL) plays a critical role in distributed systems. In these systems, data privacy and confidentiality hold paramount importance, particularly within edge-based data processing systems such as IoT devices deployed in smart…
Federated Learning (FL) enables multiple resource-constrained edge devices with varying levels of heterogeneity to collaboratively train a global model. However, devices with limited capacity can create bottlenecks and slow down model…
Unseen noise signal which is not considered in a model training process is difficult to anticipate and would lead to performance degradation. Various methods have been investigated to mitigate unseen noise. In our previous work, an…
Supervised Fine-Tuning (SFT) of large language models often suffers from task interference and catastrophic forgetting. Recent approaches alleviate this issue by isolating task-critical parameters during training. However, these methods…
Most fair machine learning methods either highly rely on the sensitive information of the training samples or require a large modification on the target models, which hinders their practical application. To address this issue, we propose a…
The challenge of solving data mining problems in e-commerce applications such as recommendation system (RS) and click-through rate (CTR) prediction is how to make inferences by constructing combinatorial features from a large number of…
Large models represent a groundbreaking advancement in multiple application fields, enabling remarkable achievements across various tasks. However, their unprecedented scale comes with significant computational costs. These models, often…
Federated Learning (FL) has emerged as a new paradigm for training machine learning models distributively without sacrificing data security and privacy. Learning models on edge devices such as mobile phones is one of the most common use…
Feature embedding learning and feature interaction modeling are two crucial components of deep models for Click-Through Rate (CTR) prediction. Most existing deep CTR models suffer from the following three problems. First, feature…
With the rise of edge computing, various AI services are expected to be available at a mobile side through the inference based on deep neural network (DNN) operated at the network edge, called edge inference (EI). On the other hand, the…
Continual learning is an emerging paradigm in machine learning, wherein a model is exposed in an online fashion to data from multiple different distributions (i.e. environments), and is expected to adapt to the distribution change.…
The expansion of large language models is increasingly limited by the constrained memory capacity of modern GPUs. To mitigate this, Mixture-of-Experts (MoE) architectures activate only a small portion of parameters during inference,…
With the proliferation of edge smart devices and the Internet of Vehicles (IoV) technologies, intelligent fatigue detection has become one of the most-used methods in our daily driving. To improve the performance of the detection model, a…
In real-world search, recommendation, and advertising systems, the multi-stage ranking architecture is commonly adopted. Such architecture usually consists of matching, pre-ranking, ranking, and re-ranking stages. In the pre-ranking stage,…