Related papers: Contrastive Multi-view Framework for Customer Life…
Contrastive learning between different views of the data achieves outstanding success in the field of self-supervised representation learning and the learned representations are useful in broad downstream tasks. Since all supervision…
Trained classification models can unintentionally lead to biased representations and predictions, which can reinforce societal preconceptions and stereotypes. Existing debiasing methods for classification models, such as adversarial…
Music similarity retrieval is fundamental for managing and exploring relevant content from large collections in streaming platforms. This paper presents a novel cross-modal contrastive learning framework that leverages the open-ended nature…
Survival analysis plays a crucial role in many healthcare decisions, where the risk prediction for the events of interest can support an informative outlook for a patient's medical journey. Given the existence of data censoring, an…
Personalized recommender systems play a crucial role in capturing users' evolving preferences over time to provide accurate and effective recommendations on various online platforms. However, many recommendation models rely on a single type…
Recent years have witnessed increasing interest in code representation learning, which aims to represent the semantics of source code into distributed vectors. Currently, various works have been proposed to represent the complex semantics…
When considering post-training quantization, prior work has typically focused on developing a mixed precision scheme or learning the best way to partition a network for quantization. In our work, CPT-V, we look at a general way to improve…
Video transformers have recently emerged as a competitive alternative to 3D CNNs for video understanding. However, due to their large number of parameters and reduced inductive biases, these models require supervised pretraining on…
Nowadays, recommender systems already impact almost every facet of peoples lives. To provide personalized high quality recommendation results, conventional systems usually train pointwise rankers to predict the absolute value of objectives…
As an algorithmic framework for learning to learn, meta-learning provides a promising solution for few-shot text classification. However, most existing research fail to give enough attention to class labels. Traditional basic framework…
Training vision-language models for image-text alignment typically requires large datasets to achieve robust performance. In low-data scenarios, standard contrastive learning can struggle to align modalities effectively due to overfitting…
Contrastive learning has proven effective in self-supervised musical representation learning, particularly for Music Information Retrieval (MIR) tasks. However, reliance on augmentation chains for contrastive view generation and the…
This paper presents a framework for learning visual representations from unlabeled video demonstrations captured from multiple viewpoints. We show that these representations are applicable for imitating several robotic tasks, including pick…
Contrastive learning has been utilized as a promising self-supervised learning approach to extract meaningful representations from unlabeled data. The majority of these methods take advantage of data-augmentation techniques to create…
Weighted twin support vector machines (WLTSVM) mines as much potential similarity information in samples as possible to improve the common short-coming of non-parallel plane classifiers. Compared with twin support vector machines (TWSVM),…
Long-term activity forecasting is an especially challenging research problem because it requires understanding the temporal relationships between observed actions, as well as the variability and complexity of human activities. Despite…
Recently, pretext-task based methods are proposed one after another in self-supervised video feature learning. Meanwhile, contrastive learning methods also yield good performance. Usually, new methods can beat previous ones as claimed that…
Contrastive learning has delivered impressive results for various tasks in the self-supervised regime. However, existing approaches optimize for learning representations specific to downstream scenarios, i.e., \textit{global}…
Many modern commercial sites employ recommender systems to propose relevant content to users. While most systems are focused on maximizing the immediate gain (clicks, purchases or ratings), a better notion of success would be the lifetime…
Pre-trained language models (LMs) store knowledge in their parameters and can generate informative responses when used in conversational systems. However, LMs suffer from the problem of "hallucination:" they may generate plausible-looking…