Related papers: Adaptive Hardness Negative Sampling for Collaborat…
Instance discriminative self-supervised representation learning has been attracted attention thanks to its unsupervised nature and informative feature representation for downstream tasks. In practice, it commonly uses a larger number of…
Recent convolutional neural networks (CNNs) have led to impressive performance but often suffer from poor calibration. They tend to be overconfident, with the model confidence not always reflecting the underlying true ambiguity and…
Adversarial training has become the primary method to defend against adversarial samples. However, it is hard to practically apply due to many shortcomings. One of the shortcomings of adversarial training is that it will reduce the…
An alternating-direction-method-based nonnegative latent factor model can perform efficient representation learning to a high-dimensional and incomplete (HDI) matrix. However, it introduces multiple hyper-parameters into the learning…
Temporal networks are effective in capturing the evolving interactions of networks over time, such as social networks and e-commerce networks. In recent years, researchers have primarily concentrated on developing specific model…
Self-supervised learning has recently shown great potential in vision tasks through contrastive learning, which aims to discriminate each image, or instance, in the dataset. However, such instance-level learning ignores the semantic…
Compressed sensing (CS) has emerged to overcome the inefficiency of Nyquist sampling. However, traditional optimization-based reconstruction is slow and can not yield an exact image in practice. Deep learning-based reconstruction has been a…
Building compact convolutional neural networks (CNNs) with reliable performance is a critical but challenging task, especially when deploying them in real-world applications. As a common approach to reduce the size of CNNs, pruning methods…
The two-tower architecture has been widely applied for learning item and user representations, which is important for large-scale recommender systems. Many two-tower models are trained using various in-batch negative sampling strategies,…
Massive datasets often contain redundancy that inflates computational costs without improving generalization. Existing data reduction methods are typically task-agnostic, discarding informative boundary samples and yielding suboptimal…
Negative sampling stands as a pivotal technique in dense retrieval, essential for training effective retrieval models and significantly impacting retrieval performance. While existing negative sampling methods have made commendable progress…
Adversarial training has shown promise in building robust models against adversarial examples. A major drawback of adversarial training is the computational overhead introduced by the generation of adversarial examples. To overcome this…
Conducting text retrieval in a dense learned representation space has many intriguing advantages over sparse retrieval. Yet the effectiveness of dense retrieval (DR) often requires combination with sparse retrieval. In this paper, we…
In general, deep neural network (DNN) pruning methods fall into two categories: 1) Weight-based deterministic constraints, and 2) Probabilistic frameworks. While each approach has its merits and limitations there are a set of common…
During the past decade, model-based recommendation methods have evolved from latent factor models to neural network-based models. Most of these techniques mainly focus on improving the overall performance, such as the root mean square error…
Collaborative filtering is used to recommend items to a user without requiring a knowledge of the item itself and tends to outperform other techniques. However, collaborative filtering suffers from the cold-start problem, which occurs when…
Data subsampling has become widely recognized as a tool to overcome computational and economic bottlenecks in analyzing massive datasets. We contribute to the development of adaptive design for estimation of finite population…
Human Activity Recognition (HAR) systems have been extensively studied by the vision and ubiquitous computing communities due to their practical applications in daily life, such as smart homes, surveillance, and health monitoring.…
State-of-the-art image models predominantly follow a two-stage strategy: pre-training on large datasets and fine-tuning with cross-entropy loss. Many studies have shown that using cross-entropy can result in sub-optimal generalisation and…
Industrial recommendation systems typically involve a two-stage process: retrieval and ranking, which aims to match users with millions of items. In the retrieval stage, classic embedding-based retrieval (EBR) methods depend on effective…