166 citations · 644 across the 58 of their papers we have counts for
11 papers · 1 filter
Continual Vision-Language Representation Learning with Off-Diagonal Information
Zixuan Ni, Longhui Wei, Siliang Tang +2
Large-scale multi-modal contrastive learning frameworks like CLIP typically require a large amount of image-text samples for training. However, these samples are always collected c…
Learning in Imperfect Environment: Multi-Label Classification with Long-Tailed Distribution and Partial Labels
Wenqiao Zhang, Changshuo Liu, Lingze Zeng +3
Conventional multi-label classification (MLC) methods assume that all samples are fully labeled and identically distributed. Unfortunately, this assumption is unrealistic in large-…
DBA: Efficient Transformer with Dynamic Bilinear Low-Rank Attention
Bosheng Qin, Juncheng Li, Siliang Tang +1
Many studies have been conducted to improve the efficiency of Transformer from quadric to linear. Among them, the low-rank-based methods aim to learn the projection matrices to com…
Robust Meta-learning with Sampling Noise and Label Noise via Eigen-Reptile
Dong Chen, Lingfei Wu, Siliang Tang +3
Recent years have seen a surge of interest in meta-learning techniques for tackling the few-shot learning (FSL) problem. However, the meta-learner is prone to overfitting since the…
Self-Supervised Class Incremental Learning
Zixuan Ni, Siliang Tang, Yueting Zhuang
Existing Class Incremental Learning (CIL) methods are based on a supervised classification framework sensitive to data labels. When updating them based on the new class data, they…
On the Efficacy of Small Self-Supervised Contrastive Models without Distillation Signals
Haizhou Shi, Youcai Zhang, Siliang Tang +4
It is a consensus that small models perform quite poorly under the paradigm of self-supervised contrastive learning. Existing methods usually adopt a large off-the-shelf model to t…
Run Away From your Teacher: Understanding BYOL by a Novel Self-Supervised Approach
Haizhou Shi, Dongliang Luo, Siliang Tang +2
Recently, a newly proposed self-supervised framework Bootstrap Your Own Latent (BYOL) seriously challenges the necessity of negative samples in contrastive learning frameworks. BYO…
Federated Unsupervised Representation Learning
Fengda Zhang, Kun Kuang, Zhaoyang You +6
To leverage enormous unlabeled data on distributed edge devices, we formulate a new problem in federated learning called Federated Unsupervised Representation Learning (FURL) to le…
Stable Prediction via Leveraging Seed Variable
Kun Kuang, Bo Li, Peng Cui +4
In this paper, we focus on the problem of stable prediction across unknown test data, where the test distribution is agnostic and might be totally different from the training one.…
Balance-Subsampled Stable Prediction
Kun Kuang, Hengtao Zhang, Fei Wu +2
In machine learning, it is commonly assumed that training and test data share the same population distribution. However, this assumption is often violated in practice because the s…
Time2Graph: Revisiting Time Series Modeling with Dynamic Shapelets
Ziqiang Cheng, Yang Yang, Wei Wang +3
Time series modeling has attracted extensive research efforts; however, achieving both reliable efficiency and interpretability from a unified model still remains a challenging pro…