DeepFM: A Factorization-Machine based Neural Network for CTR Prediction
- Huifeng Guo, Ruiming Tang, Yunming Ye, Zhenguo Li, Xiuqiang He
- Computer ScienceInternational Joint Conference on Artificial…
- 13 March 2017
This paper shows that it is possible to derive an end-to-end learning model that emphasizes both low- and high-order feature interactions, and combines the power of factorization machines for recommendation and deep learning for feature learning in a new neural network architecture.
Meta-SGD: Learning to Learn Quickly for Few Shot Learning
- Zhenguo Li, Fengwei Zhou, Fei Chen, Hang Li
- Computer Science, EducationArXiv
- 31 July 2017
Meta-SGD, an SGD-like, easily trainable meta-learner that can initialize and adapt any differentiable learner in just one step, shows highly competitive performance for few-shot learning on regression, classification, and reinforcement learning.
Segmentation using superpixels: A bipartite graph partitioning approach
- Zhenguo Li, Xiao-Ming Wu, Shih-Fu Chang
- Computer ScienceIEEE Conference on Computer Vision and Pattern…
- 16 June 2012
A novel segmentation framework based on bipartite graph partitioning is proposed, which is able to aggregate multi-layer superpixels in a principled and very effective manner and leads to a highly efficient, linear-time spectral algorithm.
DARTS+: Improved Differentiable Architecture Search with Early Stopping
- Hanwen Liang, Shifeng Zhang, Zhenguo Li
- Computer ScienceArXiv
- 13 September 2019
It is claimed that there exists overfitting in the optimization of DARTS, and a simple and effective algorithm is proposed, named "DARTS+", to avoid the collapse and improve the original DARts, by "early stopping" the search procedure when meeting a certain criterion.
Learning with Partially Absorbing Random Walks
- Xiao-Ming Wu, Zhenguo Li, Anthony Man-Cho So, John Wright, Shih-Fu Chang
- Computer ScienceNIPS
- 3 December 2012
This work proposes a novel stochastic process that is with probability αi being absorbed at current state i, and with probability 1 – αi follows a random edge out of it, and proves that under proper absorption rates, a random walk starting from a set S of low conductance will be mostly absorbed in S.
FILIP: Fine-grained Interactive Language-Image Pre-Training
- Lewei Yao, Runhu Huang, Chunjing Xu
- Computer ScienceInternational Conference on Learning…
- 9 November 2021
A large-scale Fine-grained Interactive Language-Image Pre-training (FILIP) to achieve finer-level alignment through a cross-modal late interaction mechanism, which uses a token-wise maximum similarity between visual and textual tokens to guide the contrastive objective.
DetCo: Unsupervised Contrastive Learning for Object Detection
- Enze Xie, Jian Ding, P. Luo
- Computer ScienceIEEE International Conference on Computer Vision
- 9 February 2021
Extensive experiments demonstrate that DetCo not only outperforms recent methods on a series of 2D and 3D instance-level detection tasks, but also competitive on image classification.
Federated Meta-Learning with Fast Convergence and Efficient Communication
- Fei Chen, Mi Luo, Zhenhua Dong, Zhenguo Li, Xiuqiang He
- Computer Science
- 22 February 2018
This work proposes a federated meta-learning framework FedMeta, where a parameterized algorithm (or meta-learner) is shared, instead of a global model in previous approaches, and achieves a reduction in required communication cost and increase in accuracy as compared to Federated Averaging.
Graph Edge Partitioning via Neighborhood Heuristic
- Chenzi Zhang, F. Wei, Qin Liu, Zhihao Gavin Tang, Zhenguo Li
- Computer ScienceKnowledge Discovery and Data Mining
- 4 August 2017
This paper considers the edge partitioning problem that partitions the edges of an input graph into multiple balanced components, while minimizing the total number of vertices replicated, and provides a worst-case upper bound of replication factor for this heuristic on general graphs.
One Million Scenes for Autonomous Driving: ONCE Dataset
- Jiageng Mao, Minzhe Niu, Chunjing Xu
- Computer ScienceNeurIPS Datasets and Benchmarks
- 21 June 2021
The ONCE (One millioN sCenEs) dataset for 3D object detection in the autonomous driving scenario is introduced and a benchmark is provided in which a variety of self-supervised and semi- supervised methods on the ONCE dataset are evaluated.