Related papers: StackRec: Efficient Training of Very Deep Sequenti…

Pre-training is crucial for learning deep neural networks. Most of existing pre-training methods train simple models (e.g., restricted Boltzmann machines) and then stack them layer by layer to form the deep structure. This layer-wise…

The time required for training the neural networks increases with size, complexity, and depth. Training model parameters by backpropagation inherently creates feedback loops. These loops hinder efficient pipelining and scheduling of the…

To parse images into fine-grained semantic parts, the complex fine-grained elements will put it in trouble when using off-the-shelf semantic segmentation networks. In this paper, for image parsing task, we propose to parse images from…

Transformer-based sequential recommendation (TSR) models have shown superior performance in recommendation systems, where the quality of item representations plays a crucial role. Classical representation methods integrate item features…

Recommender systems that can learn from cross-session data to dynamically predict the next item a user will choose are crucial for online platforms. However, existing approaches often use out-of-the-box sequence models which are limited by…

In the vast landscape of internet information, recommender systems (RecSys) have become essential for guiding users through a sea of choices aligned with their preferences. These systems have applications in diverse domains, such as news…

Training deep networks is expensive and time-consuming with the training period increasing with data size and growth in model parameters. In this paper, we provide a framework for distributed training of deep networks over a cluster of CPUs…

Modern recommender systems must adapt to dynamic, need-specific objectives for diverse recommendation scenarios, yet most traditional recommenders are optimized for a single static target and struggle to reconfigure behavior on demand.…

The sequential recommender (SR) system is a crucial component of modern recommender systems, as it aims to capture the evolving preferences of users. Significant efforts have been made to enhance the capabilities of SR systems. These…

While sequential recommendation achieves significant progress on capturing user-item transition patterns, transferring such large-scale recommender systems remains challenging due to the disjoint user and item groups across domains. In this…

Sequential recommendation models have achieved state-of-the-art performance using self-attention mechanism. It has since been found that moving beyond only using item ID and positional embeddings leads to a significant accuracy boost when…

Recurrent neural networks have been widely used in sequence learning tasks. In previous studies, the performance of the model has always been improved by either wider or deeper structures. However, the former becomes more prone to…

Deep learning based recommendation systems form the backbone of most personalized cloud services. Though the computer architecture community has recently started to take notice of deep recommendation inference, the resulting solutions have…

Deep convolutional neural networks (CNNs) have achieved remarkable success in various fields. However, training an excellent CNN is practically a trial-and-error process that consumes a tremendous amount of time and computer resources. To…

Sequential Recommendation is a popular recommendation task that uses the order of user-item interaction to model evolving users' interests and sequential patterns in their behaviour. Current state-of-the-art Transformer-based models for…

We propose a distributed approach to train deep neural networks (DNNs), which has guaranteed convergence theoretically and great scalability empirically: close to 6 times faster on instance of ImageNet data set when run with 6 machines. The…

Deep learning methods are useful for high-dimensional data and are becoming widely used in many areas of software engineering. Deep learners utilizes extensive computational power and can take a long time to train-- making it difficult to…

News recommendation is critical for personalized news access. Most existing news recommendation methods rely on centralized storage of users' historical news click behavior data, which may lead to privacy concerns and hazards. Federated…

Convolutional neural networks (CNNs) have constantly achieved better performance over years by introducing more complex topology, and enlarging the capacity towards deeper and wider CNNs. This makes the manual design of CNNs extremely…

Deep reinforcement learning yields great results for a large array of problems, but models are generally retrained anew for each new problem to be solved. Prior learning and knowledge are difficult to incorporate when training new models,…