Related papers: On-Device Next-Item Recommendation with Self-Super…
Knowledge distillation compacts deep networks by letting a small student network learn from a large teacher network. The accuracy of knowledge distillation recently benefited from adding residual layers. We propose to reduce the size of the…
This thesis investigates dataset downsampling as a strategy to optimize energy efficiency in recommender systems while maintaining competitive performance. With increasing dataset sizes posing computational and environmental challenges,…
Sequential recommendation aims to capture user preferences by modeling sequential patterns in user-item interactions. However, these models are often influenced by noise such as accidental interactions, leading to suboptimal performance.…
Recommender system is a very promising way to address the problem of overabundant information for online users. Though the information filtering for the online commercial systems received much attention recently, almost all of the previous…
Recent advances in model compression have provided procedures for compressing large neural networks to a fraction of their original size while retaining most if not all of their accuracy. However, all of these approaches rely on access to…
Online relevance matching is an essential task of e-commerce product search to boost the utility of search engines and ensure a smooth user experience. Previous work adopts either classical relevance matching models or Transformer-style…
In today's data-driven world, recommender systems (RS) play a crucial role to support the decision-making process. As users become continuously connected to the internet, they become less patient and less tolerant to obsolete…
As pretrained transformer language models continue to achieve state-of-the-art performance, the Natural Language Processing community has pushed for advances in model compression and efficient attention mechanisms to address high…
Knowledge distillation is an effective way for model compression in deep learning. Given a large model (i.e., teacher model), it aims to improve the performance of a compact model (i.e., student model) by transferring the information from…
One of the main challenges in recommender systems is data sparsity which leads to high variance. Several attempts have been made to improve the bias-variance trade-off using auxiliary information. In particular, document modeling-based…
We present a novel class incremental learning approach based on deep neural networks, which continually learns new tasks with limited memory for storing examples in the previous tasks. Our algorithm is based on knowledge distillation and…
Resource-constrained perception systems such as edge computing and vision-for-robotics require vision models to be both accurate and lightweight in computation and memory usage. While knowledge distillation is a proven strategy to enhance…
Semantic correspondence, the task of determining relationships between different parts of images, underpins various applications including 3D reconstruction, image-to-image translation, object tracking, and visual place recognition. Recent…
Recommender systems are significant to help people deal with the world of information explosion and overload. In this Letter, we develop a general framework named self-consistent refinement and implement it be embedding two representative…
Recommender systems presently utilize vast amounts of data and play a pivotal role in enhancing user experiences. Graph Convolution Networks (GCNs) have surfaced as highly efficient models within the realm of recommender systems due to…
Deep learning architectures have shown remarkable results in scene understanding problems, however they exhibit a critical drop of performances when they are required to learn incrementally new tasks without forgetting old ones. This…
In the last decade we have observed a mass increase of information, in particular information that is shared through smartphones. Consequently, the amount of information that is available does not allow the average user to be aware of all…
Knowledge distillation is considered a compression mechanism when judged on the resulting student's accuracy and loss, yet its functional impact is poorly understood. We quantify the compression capacity of knowledge distillation and the…
With the recent advancements in information technology there has been a huge surge in amount of data available. But information retrieval technology has not been able to keep up with this pace of information generation resulting in over…
The use of mobile devices in combination with the rapid growth of the internet has generated an information overload problem. Recommender systems is a necessity to decide which of the data are relevant to the user. However in mobile devices…