Limeng Cui
Limeng Cui has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Suhang Wang
The Pennsylvania State University, State College, USA
3 shared publications - Bing Yin
Amazon, Palo Alto, USA
2 shared publications - Monica Cheng
Amazon, Palo Alto, CA, USA
2 shared publications - Sreyashi Nag
Amazon, Palo Alto, CA, USA
2 shared publications - Xianfeng Tang
Amazon, Palo Alto, CA, USA
2 shared publications - Yinghan Wang
Amazon, Palo Alto, USA
2 shared publications
Latest Publications
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Agent A/B: Automated and Scalable A/B Testing on Live Websites with Interactive LLM Agents
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Open AccessAgent A/B: Automated and Scalable A/B Testing on Live Websites with Interactive LLM Agents
- Open Access
- 13 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 338-345
Hierarchical Query Classification in E-commerce Search
- 13 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 338-345
Open AccessHierarchical Query Classification in E-commerce Search
- Open Access
- 4 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 368-379
A Unified Framework of Graph Information Bottleneck for Robustness and Membership Privacy
Graph Neural Networks (GNNs) have achieved great success in modeling graph-structured data. However, recent works show that GNNs are vulnerable to adversarial attacks which can fool the GNN model to make desired predictions of the attacker. In addition, training data of GNNs can be leaked under membership inference attacks. This largely hinders the adoption of GNNs in high-stake domains such as e-commerce, finance and bioinformatics. Though investigations have been made in conducting robust predictions and protecting membership privacy, they generally fail to simultaneously consider the robustness and membership privacy. Therefore, in this work, we study a novel problem of developing robust and membership privacy-preserving GNNs. Our analysis shows that Information Bottleneck (IB) can help filter out noisy information and regularize the predictions on labeled samples, which can benefit robustness and membership privacy. However, structural noises and lack of labels in node classification challenge the deployment of IB on graph-structured data. To mitigate these issues, we propose a novel graph information bottleneck framework that can alleviate structural noises with neighbor bottleneck. Pseudo labels are also incorporated in the optimization to minimize the gap between the predictions on the labeled set and unlabeled set for membership privacy. Extensive experiments on real-world datasets demonstrate that our method can give robust predictions and simultaneously preserve membership privacy.
- 4 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 368-379
Open AccessA Unified Framework of Graph Information Bottleneck for Robustness and Membership Privacy
Graph Neural Networks (GNNs) have achieved great success in modeling graph-structured data. However, recent works show that GNNs are vulnerable to adversarial attacks which can fool the GNN model to make desired predictions of the attacker. In addition, training data of GNNs can be leaked under membership inference attacks. This largely hinders the adoption of GNNs in high-stake domains such as e-commerce, finance and bioinformatics. Though investigations have been made in conducting robust predictions and protecting membership privacy, they generally fail to simultaneously consider the robustness and membership privacy. Therefore, in this work, we study a novel problem of developing robust and membership privacy-preserving GNNs. Our analysis shows that Information Bottleneck (IB) can help filter out noisy information and regularize the predictions on labeled samples, which can benefit robustness and membership privacy. However, structural noises and lack of labels in node classification challenge the deployment of IB on graph-structured data. To mitigate these issues, we propose a novel graph information bottleneck framework that can alleviate structural noises with neighbor bottleneck. Pseudo labels are also incorporated in the optimization to minimize the gap between the predictions on the labeled set and unlabeled set for membership privacy. Extensive experiments on real-world datasets demonstrate that our method can give robust predictions and simultaneously preserve membership privacy.
- Open Access
- 4 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 5162-5173
Exploiting Intent Evolution in E-commercial Query Recommendation
Aiming at a better understanding of the search goals in the user search sessions, recent query recommender systems explicitly model the reformulations of queries, which hopes to estimate the intents behind these reformulations and thus benefit the next-query recommendation. However, in real-world e-commercial search scenarios, user intents are much more complicated and may evolve dynamically. Existing methods merely consider trivial reformulation intents from semantic aspects and fail to model dynamic reformulation intent flows in search sessions, leading to sub-optimal capacities to recommend desired queries. To deal with these limitations, we first explicitly define six types of query reformulation intents according to the desired products of two consecutive queries. We then apply two self-attentive encoders on top of two pre-trained large language models to learn the transition dynamics from semantic query and intent reformulation sequences, respectively. We develop an intent-aware query decoder to utilize the predicted intents for suggesting the next queries. We instantiate such a framework with an Intent-aware Variational AutoEncoder (IVAE) under deployment at Amazon. We conduct comprehensive experiments on two real-world e-commercial datasets from Amazon and one public dataset from BestBuy. Specifically, IVAE improves the Recall@15 by 25.44% and 60.47% on two Amazon datasets and 13.91% on BestBuy, respectively.
- 4 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 5162-5173
Open AccessExploiting Intent Evolution in E-commercial Query Recommendation
Aiming at a better understanding of the search goals in the user search sessions, recent query recommender systems explicitly model the reformulations of queries, which hopes to estimate the intents behind these reformulations and thus benefit the next-query recommendation. However, in real-world e-commercial search scenarios, user intents are much more complicated and may evolve dynamically. Existing methods merely consider trivial reformulation intents from semantic aspects and fail to model dynamic reformulation intent flows in search sessions, leading to sub-optimal capacities to recommend desired queries. To deal with these limitations, we first explicitly define six types of query reformulation intents according to the desired products of two consecutive queries. We then apply two self-attentive encoders on top of two pre-trained large language models to learn the transition dynamics from semantic query and intent reformulation sequences, respectively. We develop an intent-aware query decoder to utilize the predicted intents for suggesting the next queries. We instantiate such a framework with an Intent-aware Variational AutoEncoder (IVAE) under deployment at Amazon. We conduct comprehensive experiments on two real-world e-commercial datasets from Amazon and one public dataset from BestBuy. Specifically, IVAE improves the Recall@15 by 25.44% and 60.47% on two Amazon datasets and 13.91% on BestBuy, respectively.
- 29 November 2022
- Published by Springer Nature in AI & SOCIETY
- Vol. 38 (3) , 1185-1192
Street surface condition of wealthy and poor neighborhoods: the case of Los Angeles
- 29 November 2022
- Published by Springer Nature in AI & SOCIETY
- Vol. 38 (3) , 1185-1192
Street surface condition of wealthy and poor neighborhoods: the case of Los Angeles