Alert button
Picture for Yukun Chen

Yukun Chen

Alert button

Towards the Better Ranking Consistency: A Multi-task Learning Framework for Early Stage Ads Ranking

Jul 12, 2023
Xuewei Wang, Qiang Jin, Shengyu Huang, Min Zhang, Xi Liu, Zhengli Zhao, Yukun Chen, Zhengyu Zhang, Jiyan Yang, Ellie Wen, Sagar Chordia, Wenlin Chen, Qin Huang

Figure 1 for Towards the Better Ranking Consistency: A Multi-task Learning Framework for Early Stage Ads Ranking
Figure 2 for Towards the Better Ranking Consistency: A Multi-task Learning Framework for Early Stage Ads Ranking
Figure 3 for Towards the Better Ranking Consistency: A Multi-task Learning Framework for Early Stage Ads Ranking
Figure 4 for Towards the Better Ranking Consistency: A Multi-task Learning Framework for Early Stage Ads Ranking

Dividing ads ranking system into retrieval, early, and final stages is a common practice in large scale ads recommendation to balance the efficiency and accuracy. The early stage ranking often uses efficient models to generate candidates out of a set of retrieved ads. The candidates are then fed into a more computationally intensive but accurate final stage ranking system to produce the final ads recommendation. As the early and final stage ranking use different features and model architectures because of system constraints, a serious ranking consistency issue arises where the early stage has a low ads recall, i.e., top ads in the final stage are ranked low in the early stage. In order to pass better ads from the early to the final stage ranking, we propose a multi-task learning framework for early stage ranking to capture multiple final stage ranking components (i.e. ads clicks and ads quality events) and their task relations. With our multi-task learning framework, we can not only achieve serving cost saving from the model consolidation, but also improve the ads recall and ranking consistency. In the online A/B testing, our framework achieves significantly higher click-through rate (CTR), conversion rate (CVR), total value and better ads-quality (e.g. reduced ads cross-out rate) in a large scale industrial ads ranking system.

* Accepted by AdKDD 23 
Viaarxiv icon

Boxhead: A Dataset for Learning Hierarchical Representations

Oct 07, 2021
Yukun Chen, Frederik Träuble, Andrea Dittadi, Stefan Bauer, Bernhard Schölkopf

Figure 1 for Boxhead: A Dataset for Learning Hierarchical Representations
Figure 2 for Boxhead: A Dataset for Learning Hierarchical Representations
Figure 3 for Boxhead: A Dataset for Learning Hierarchical Representations
Figure 4 for Boxhead: A Dataset for Learning Hierarchical Representations

Disentanglement is hypothesized to be beneficial towards a number of downstream tasks. However, a common assumption in learning disentangled representations is that the data generative factors are statistically independent. As current methods are almost solely evaluated on toy datasets where this ideal assumption holds, we investigate their performance in hierarchical settings, a relevant feature of real-world data. In this work, we introduce Boxhead, a dataset with hierarchically structured ground-truth generative factors. We use this novel dataset to evaluate the performance of state-of-the-art autoencoder-based disentanglement models and observe that hierarchical models generally outperform single-layer VAEs in terms of disentanglement of hierarchically arranged factors.

Viaarxiv icon

MEBOW: Monocular Estimation of Body Orientation In the Wild

Nov 27, 2020
Chenyan Wu, Yukun Chen, Jiajia Luo, Che-Chun Su, Anuja Dawane, Bikramjot Hanzra, Zhuo Deng, Bilan Liu, James Wang, Cheng-Hao Kuo

Figure 1 for MEBOW: Monocular Estimation of Body Orientation In the Wild
Figure 2 for MEBOW: Monocular Estimation of Body Orientation In the Wild
Figure 3 for MEBOW: Monocular Estimation of Body Orientation In the Wild
Figure 4 for MEBOW: Monocular Estimation of Body Orientation In the Wild

Body orientation estimation provides crucial visual cues in many applications, including robotics and autonomous driving. It is particularly desirable when 3-D pose estimation is difficult to infer due to poor image resolution, occlusion or indistinguishable body parts. We present COCO-MEBOW (Monocular Estimation of Body Orientation in the Wild), a new large-scale dataset for orientation estimation from a single in-the-wild image. The body-orientation labels for around 130K human bodies within 55K images from the COCO dataset have been collected using an efficient and high-precision annotation pipeline. We also validated the benefits of the dataset. First, we show that our dataset can substantially improve the performance and the robustness of a human body orientation estimation model, the development of which was previously limited by the scale and diversity of the available training data. Additionally, we present a novel triple-source solution for 3-D human pose estimation, where 3-D pose labels, 2-D pose labels, and our body-orientation labels are all used in joint training. Our model significantly outperforms state-of-the-art dual-source solutions for monocular 3-D human pose estimation, where training only uses 3-D pose labels and 2-D pose labels. This substantiates an important advantage of MEBOW for 3-D human pose estimation, which is particularly appealing because the per-instance labeling cost for body orientations is far less than that for 3-D poses. The work demonstrates high potential of MEBOW in addressing real-world challenges involving understanding human behaviors. Further information of this work is available at https://chenyanwu.github.io/MEBOW/.

* Accepted by CVPR2020 
Viaarxiv icon

Detecting Comma-shaped Clouds for Severe Weather Forecasting using Shape and Motion

Jun 06, 2018
Xinye Zheng, Jianbo Ye, Yukun Chen, Stephen Wistar, Jia Li, Jose A. Piedra-Fernández, Michael A. Steinberg, James Z. Wang

Figure 1 for Detecting Comma-shaped Clouds for Severe Weather Forecasting using Shape and Motion
Figure 2 for Detecting Comma-shaped Clouds for Severe Weather Forecasting using Shape and Motion
Figure 3 for Detecting Comma-shaped Clouds for Severe Weather Forecasting using Shape and Motion
Figure 4 for Detecting Comma-shaped Clouds for Severe Weather Forecasting using Shape and Motion

Meteorologists use shapes and movements of clouds in satellite images as indicators of several major types of severe storms. Satellite imaginary data are in increasingly higher resolution, both spatially and temporally, making it impossible for humans to fully leverage the data in their forecast. Automatic satellite imagery analysis methods that can find storm-related cloud patterns as soon as they are detectable are in demand. We propose a machine learning and pattern recognition based approach to detect "comma-shaped" clouds in satellite images, which are specific cloud distribution patterns strongly associated with the cyclone formulation. In order to detect regions with the targeted movement patterns, our method is trained on manually annotated cloud examples represented by both shape and motion-sensitive features. Sliding windows in different scales are used to ensure that dense clouds will be captured, and we implement effective selection rules to shrink the region of interest among these sliding windows. Finally, we evaluate the method on a hold-out annotated comma-shaped cloud dataset and cross-match the results with recorded storm events in the severe weather database. The validated utility and accuracy of our method suggest a high potential for assisting meteorologists in weather forecasting.

* Under submission 
Viaarxiv icon

Aggregated Wasserstein Metric and State Registration for Hidden Markov Models

Nov 19, 2017
Yukun Chen, Jianbo Ye, Jia Li

Figure 1 for Aggregated Wasserstein Metric and State Registration for Hidden Markov Models
Figure 2 for Aggregated Wasserstein Metric and State Registration for Hidden Markov Models
Figure 3 for Aggregated Wasserstein Metric and State Registration for Hidden Markov Models
Figure 4 for Aggregated Wasserstein Metric and State Registration for Hidden Markov Models

We propose a framework, named Aggregated Wasserstein, for computing a dissimilarity measure or distance between two Hidden Markov Models with state conditional distributions being Gaussian. For such HMMs, the marginal distribution at any time position follows a Gaussian mixture distribution, a fact exploited to softly match, aka register, the states in two HMMs. We refer to such HMMs as Gaussian mixture model-HMM (GMM-HMM). The registration of states is inspired by the intrinsic relationship of optimal transport and the Wasserstein metric between distributions. Specifically, the components of the marginal GMMs are matched by solving an optimal transport problem where the cost between components is the Wasserstein metric for Gaussian distributions. The solution of the optimization problem is a fast approximation to the Wasserstein metric between two GMMs. The new Aggregated Wasserstein distance is a semi-metric and can be computed without generating Monte Carlo samples. It is invariant to relabeling or permutation of states. The distance is defined meaningfully even for two HMMs that are estimated from data of different dimensionality, a situation that can arise due to missing variables. This distance quantifies the dissimilarity of GMM-HMMs by measuring both the difference between the two marginal GMMs and that between the two transition matrices. Our new distance is tested on tasks of retrieval, classification, and t-SNE visualization of time series. Experiments on both synthetic and real data have demonstrated its advantages in terms of accuracy as well as efficiency in comparison with existing distances based on the Kullback-Leibler divergence.

* Our manuscript is based on our conference paper [arXiv:1608.01747] published in 14th European Conference on Computer Vision (ECCV 2016, spotlight). It has been significantly extended and is now in journal submission 
Viaarxiv icon

A Distance for HMMs based on Aggregated Wasserstein Metric and State Registration

Aug 05, 2016
Yukun Chen, Jianbo Ye, Jia Li

Figure 1 for A Distance for HMMs based on Aggregated Wasserstein Metric and State Registration
Figure 2 for A Distance for HMMs based on Aggregated Wasserstein Metric and State Registration
Figure 3 for A Distance for HMMs based on Aggregated Wasserstein Metric and State Registration
Figure 4 for A Distance for HMMs based on Aggregated Wasserstein Metric and State Registration

We propose a framework, named Aggregated Wasserstein, for computing a dissimilarity measure or distance between two Hidden Markov Models with state conditional distributions being Gaussian. For such HMMs, the marginal distribution at any time spot follows a Gaussian mixture distribution, a fact exploited to softly match, aka register, the states in two HMMs. We refer to such HMMs as Gaussian mixture model-HMM (GMM-HMM). The registration of states is inspired by the intrinsic relationship of optimal transport and the Wasserstein metric between distributions. Specifically, the components of the marginal GMMs are matched by solving an optimal transport problem where the cost between components is the Wasserstein metric for Gaussian distributions. The solution of the optimization problem is a fast approximation to the Wasserstein metric between two GMMs. The new Aggregated Wasserstein distance is a semi-metric and can be computed without generating Monte Carlo samples. It is invariant to relabeling or permutation of the states. This distance quantifies the dissimilarity of GMM-HMMs by measuring both the difference between the two marginal GMMs and the difference between the two transition matrices. Our new distance is tested on the tasks of retrieval and classification of time series. Experiments on both synthetic data and real data have demonstrated its advantages in terms of accuracy as well as efficiency in comparison with existing distances based on the Kullback-Leibler divergence.

* submitted to ECCV 2016 
Viaarxiv icon