Yuening Li

Yuening Li

Auto-generated profile, based on publicly available information

Yuening Li

Google, Mountain View, USA

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 September 2021 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
YLYuening Li
Yuening Li
ZCZhengzhang Chen
Zhengzhang Chen
DZDaochen Zha
Daochen Zha
KZKaixiong Zhou
Kaixiong Zhou
HJHaifeng Jin
Haifeng Jin
XHXia Hu
Xia Hu
Anomaly detection is an important data mining task with numerous applications, such as intrusion detection, credit card fraud detection, and video surveillance. However, given a specific complicated task with complicated data, the process of building an effective deep learning-based system for anomaly detection still highly relies on human expertise and laboring trials. Also, while neural architecture search (NAS) has shown its promise in discovering effective deep architectures in various domains, such as image classification, object detection, and semantic segmentation, contemporary NAS methods are not suitable for anomaly detection due to the lack of intrinsic search space, unstable search process, and low sample efficiency. To bridge the gap, in this article, we propose AutoADe, an automated anomaly detection framework, which aims to search for an optimal neural network model within a predefined search space. Specifically, we first design a curiosity-guided search strategy to overcome the curse of local optimality. A controller, which acts as a search agent, is encouraged to take actions to maximize the information gain about the controller's internal belief. We further introduce an experience replay mechanism based on self-imitation learning to improve the sample efficiency. Experimental results on various real-world benchmark datasets demonstrate that the deep model identified by AutoAD achieves the best performance, comparing with existing handcrafted models and traditional search methods.

4 March 2024
Verified
Conference Paper
Open access
YSYi Su
Yi Su
XWXiangyu Wang
Xiangyu Wang
ELElaine Ya Le
Elaine Ya Le
LLLiang Liu
Liang Liu
YLYuening Li
Yuening Li
MCMinmin Chen
Minmin Chen

21 October 2023
Verified
Conference Paper
Open access
QLQingyun Liu
Qingyun Liu
ZZZhe Zhao
Zhe Zhao
LLLiang Liu
Liang Liu
ZZZhen Zhang
Zhen Zhang
JSJunjie Shan
Junjie Shan
ECEd H. Chi
Ed H. Chi
In recent years, social media users spend significant amount of time on Short-Form Video (SFV) platforms. Its success in creating an immersive viewership experience is not only from the content, but also due to its unique UI innovation: instead of providing choices for users to click, SFV platforms actively recommend content to users to watch one at a time. In this paper, we highlight unique challenges rooted from such UI changes for SFV recommendation system design. Firstly, there is yet much unexplored for sources of system biases under the new UI, as there are no clicks nor the common click-based position biases. Additionally, when training multiple types of user activities, positive labels for activities like sharing and commenting can be much sparser and more skewed than traditional click-based recommendation systems, as the latter can filter non-click impressions when generating "post-click" activities. To tackle these challenges, we introduce a unified multi-task ranking framework which puts two novel components all together into an overall system for SFV recommendation. First, we identify that there are position biases of SFVs in the recommendation sequence, namely "watch trail biases", and introduce biases correction using trail-related information. Second, to get the most benefits from multi-task learning, especially co-training tasks with extremely skewed and sparse labels, we adapt a disentangle regularization to mitigate task conflicts, introduce loss upweighting for sparse task co-training and adopt a meta-learning algorithm for efficient weight selection. We demonstrate the effectiveness and efficiency of the framework on one of today's largest SFV platforms. Our framework has been deployed to the production system for more than 6 months.

2 March 2021 in Security and Communication Networks
Verified
Journal Article
Open access
PDF file
MLMing Li
Ming Li
LQLi Qin-Sheng
Li Qin-Sheng
YLYuening Li
Yuening Li
YCYunkun Cui
Yunkun Cui
XZXiufeng Zhao
Xiufeng Zhao
LGLei Guo
Lei Guo
The level of technical and tactical decision-making in a tennis game has a very important impact on the outcome of the game. How to discover the characteristics and rules of the game from a large amount of technical and tactical data, how to overcome the shortcomings of traditional statistical methods, and how to provide a scientific basis for correct decision-making are a top priority. Based on 5G and association analysis data mining theory, we established a data mining model for tennis technical offensive tactics and association rules and conducted specific case studies. It can calculate the maximization and distribution rate of certain technologies, also distinguish between the athlete’s gain and loss rate and the spatial position on the track, and use artificial statistical methods to cause errors and subjective participation. This solution provides objective and scientific decision support for this problem and is used in the decision-making of the landing point in tennis match technology and tactics. Experimental simulation shows that the data mining technology analysis system used for regional tennis matches is more concise, efficient, and accurate than traditional movie analysis methods.

24 August 2024
Verified
Conference Paper
Open access
YSYi Su
Yi Su
HLHaokai Lu
Haokai Lu
YLYuening Li
Yuening Li
LLLiang Liu
Liang Liu
SBShuchao Bi
Shuchao Bi
MCMinmin Chen
Minmin Chen
Exposure bias and its induced feedback loop effect are well-known problems in recommender systems. Exploration is believed to be the key to break such feedback loops. While classical contextual bandit algorithms such as Upper-Confidence-Bound and Thompson Sampling have been successful in addressing the exploration-exploitation trade-off in the single-task settings with one clear reward signal, modern recommender systems often leverage multiple rich sources of feedback such as clicks, likes, dislikes, shares, satisfaction survey responses, and employ multi-task learning in practice. It is unclear how one can incorporate exploration in the multi-task setup with different objectives. In this paper, we study an efficient bandit algorithm tailored to multi-task recommender systems, named Multi-task Neural Linear Bandit (mtNLB). In particular, we investigate efficient feature embeddings in the multi-task setups that could be used as contextual features in the Neural Linear Bandit, a contextual bandit algorithm that nicely combines the representation power from DNN and simplicity in uncertainty calculation from linear models. We further study cost-effective approximations of the uncertainty estimate and principled ways to incorporate uncertainty into the multi-task scoring of items. To showcase the efficacy of our proposed method, we conduct live experiments on a large-scale commercial recommendation platform that serves billions of users. We evaluate the quality of the uncertainty estimate and demonstrate its ability to improve exploration across the different dimensions of the reward signals in comparison to baseline approaches.

12 June 2020 in arXiv
Verified
Preprint
Open access
PDF file
KZKaixiong Zhou
Kaixiong Zhou
Xiao HuangXiao Huang
Xiao Huang
YLYuening Li
Yuening Li
DZDaochen Zha
Daochen Zha
RCRui Chen
Rui Chen
XHXia Hu
Xia Hu
Graph neural networks (GNNs), which learn the representation of a node by aggregating its neighbors, have become an effective computational tool in downstream applications. Over-smoothing is one of the key issues which limit the performance of GNNs as the number of layers increases. It is because the stacked aggregators would make node representations converge to indistinguishable vectors. Several attempts have been made to tackle the issue by bringing linked node pairs close and unlinked pairs distinct. However, they often ignore the intrinsic community structures and would result in sub-optimal performance. The representations of nodes within the same community/class need be similar to facilitate the classification, while different classes are expected to be separated in embedding space. To bridge the gap, we introduce two over-smoothing metrics and a novel technique, i.e., differentiable group normalization (DGN). It normalizes nodes within the same group independently to increase their smoothness, and separates node distributions among different groups to significantly alleviate the over-smoothing issue. Experiments on real-world datasets demonstrate that DGN makes GNN models more robust to over-smoothing and achieves better performance with deeper GNNs.