Related papers: Weakly-supervised Temporal Path Representation Lea…

We introduce the Temporal Contrastive Transformer (TCT), a representation learning framework designed to capture contextual temporal dynamics in sequences of financial transactions. The model is trained using a self-supervised contrastive…

In this paper, a new reinforcement learning (RL) method known as the method of temporal differential is introduced. Compared to the traditional temporal-difference learning method, it plays a crucial role in developing novel RL techniques…

Contrastive language-audio pretraining, which aims to unify multimodal representations in a shared embedding space, serves as a cornerstone for building a wide range of applications, from cross-modal retrieval to cutting-edge multimodal…

Graph contrastive learning has emerged as a powerful tool for unsupervised graph representation learning. The key to the success of graph contrastive learning is to acquire high-quality positive and negative samples as contrasting pairs for…

Creating labeled training sets has become one of the major roadblocks in machine learning. To address this, recent \emph{Weak Supervision (WS)} frameworks synthesize training labels from multiple potentially noisy supervision sources.…

Vast quantities of person-generated health data (wearables) are collected but the process of annotating to feed to machine learning models is impractical. This paper discusses ways in which self-supervised approaches that use contrastive…

Deep neural network-based classifiers trained with the categorical cross-entropy (CCE) loss are sensitive to label noise in the training data. One common type of method that can mitigate the impact of label noise can be viewed as supervised…

Place recognition is an essential and challenging task in loop closing and global localization for robotics and autonomous driving applications. Benefiting from the recent advances in deep learning techniques, the performance of LiDAR place…

In this paper we show that learning video feature spaces in which temporal cycles are maximally predictable benefits action classification. In particular, we propose a novel learning approach termed Cycle Encoding Prediction (CEP) that is…

Graph representation learning (GRL) makes considerable progress recently, which encodes graphs with topological structures into low-dimensional embeddings. Meanwhile, the time-consuming and costly process of annotating graph labels manually…

Contrastive self-supervised learning (SSL) learns an embedding space that maps similar data pairs closer and dissimilar data pairs farther apart. Despite its success, one issue has been overlooked: the fairness aspect of representations…

Deep-learning-based automated segmentation of vascular structures in preoperative CT scans contributes to computer-assisted diagnosis and intervention procedure in vascular diseases. While CT angiography (CTA) is the common standard,…

Temporal knowledge graphs (TKGs) have been identified as a promising approach to represent the dynamics of facts along the timeline. The extrapolation of TKG is to predict unknowable facts happening in the future, holding significant…

Learning discriminative image representations plays a vital role in long-tailed image classification because it can ease the classifier learning in imbalanced cases. Given the promising performance contrastive learning has shown recently in…

Sequential recommendation methods play a crucial role in modern recommender systems because of their ability to capture a user's dynamic interest from her/his historical interactions. Despite their success, we argue that these approaches…

Self-supervised learning is a machine learning approach that generates implicit labels by learning underlined patterns and extracting discriminative features from unlabeled data without manual labelling. Contrastive learning introduces the…

Node classification in real world graphs often suffers from label scarcity and noise, especially in high stakes domains like human trafficking detection and misinformation monitoring. While direct supervision is limited, such graphs…

Contrastive learning has moved the state of the art for many tasks in computer vision and information retrieval in recent years. This poster is the first work that applies supervised contrastive learning to the task of product matching in…

Accurate and robust image-based geo-localization at a global scale is challenging due to diverse environments, visually ambiguous scenes, and the lack of distinctive landmarks in many regions. While contrastive learning methods show…

In this work, we focus on robust time series representation learning. Our assumption is that real-world time series is noisy and complementary information from different views of the same time series plays an important role while analyzing…