Related papers: Predicate Transfer: Efficient Pre-Filtering on Mul…

Transfer learning has emerged as a powerful methodology for adapting pre-trained deep neural networks on image recognition tasks to new domains. This process consists of taking a neural network pre-trained on a large feature-rich source…

Cross-domain recommendation has attracted substantial interest in industrial apps such as Meituan, which serves multiple business domains via knowledge transfer and meets the diverse interests of users. However, existing methods typically…

The field of transfer learning is undergoing a significant shift with the introduction of large pretrained models which have demonstrated strong adaptability to a variety of downstream tasks. However, the high computational and memory…

Many applications of approximate membership query data structures, or filters, require only an incremental filter that supports insertions but not deletions. However, the design space of incremental filters is missing a "sweet spot" filter…

Declarative data quality has been an active research topic. The fundamental principle behind a declarative approach to data quality is the use of declarative statements to realize data quality primitives on top of any relational data…

Transfer learning enhances learning across tasks, by leveraging previously learned representations -- if they are properly chosen. We describe an efficient method to accurately estimate the appropriateness of a previously trained model for…

Recent work has suggested enhancing Bloom filters by using a pre-filter, based on applying machine learning to model the data set the Bloom filter is meant to represent. Here we model such learned Bloom filters, clarifying what guarantees…

Transfer learning is beneficial for survival analysis, especially when the target study has a limited number of events. However, existing transfer learning methods rely on the restrictive assumption that the target and source studies share…

Routing algorithms for public transport, particularly the widely used RAPTOR and its variants, often face performance bottlenecks during the transfer relaxation phase, especially on dense transfer graphs, when supporting unlimited…

Central to the success of Transformers is the attention block, which effectively models global dependencies among input tokens associated to a dataset. However, we theoretically demonstrate that standard attention mechanisms in transformers…

Deep neural networks produce state-of-the-art results when trained on a large number of labeled examples but tend to overfit when small amounts of labeled examples are used for training. Creating a large number of labeled examples requires…

Transfer learning approaches have shown to significantly improve performance on downstream tasks. However, it is common for prior works to only report where transfer learning was beneficial, ignoring the significant trial-and-error required…

Offline paired preference optimization algorithms have become a popular approach for fine-tuning on preference data, outperforming traditional supervised fine-tuning in various tasks. However, traditional implementations often involve…

One of the main motivations of studying continual learning is that the problem setting allows a model to accrue knowledge from past tasks to learn new tasks more efficiently. However, recent studies suggest that the key metric that…

Parameter-efficient fine-tuning approaches have recently garnered a lot of attention. Having considerably lower number of trainable weights, these methods can bring about scalability and computational effectiveness. In this paper, we look…

Real-word search and recommender systems usually adopt a multi-stage ranking architecture, including matching, pre-ranking, ranking, and re-ranking. Previous works mainly focus on the ranking stage while very few focus on the pre-ranking…

In this paper, we introduce a new regularization technique for transfer learning. The aim of the proposed approach is to capture statistical relationships among convolution filters learned from a well-trained network and transfer this…

Sorting is a fundamental and well studied problem that has been studied extensively. Sorting plays an important role in the area of databases, as many queries can be served much faster if the relations are first sorted. One of the most…

In the theory of conditional sets, many classical theorems from areas such as functional analysis, probability theory or measure theory are lifted to a conditional framework, often to be applied in areas such as mathematical economics or…

Transfer learning is a widely used method to build high performing computer vision models. In this paper, we study the efficacy of transfer learning by examining how the choice of data impacts performance. We find that more pre-training…