Liuhui Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Liuhui Wang has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Fuli Feng
National University of Singapore, Singapore, Singapore
2 shared publications - Tat-Seng Chua
National University of Singapore, Singapore, Singapore
2 shared publications - Wenjie Wang
National University of Singapore, Singapore, Singapore
2 shared publications - Xinyu Lin
National University of Singapore, Singapore, Singapore
2 shared publications - Aditya Akella
The University of Texas at Austin, Austin, TX, USA
1 shared publication Dermatology
The Chinese version of this Expert Consensus has been published on Chinese Journal of Dermology, 2019, 52(10): 711-716
1 shared publication
Latest Publications
- Open Access
- 8 December 2023
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Management of Data
- Vol. 1 (4) , 1-27
ChainedFilter: Combining Membership Filters by Chain Rule
Membership (membership query/membership testing) is a fundamental problem across databases, networks and security. However, previous research has primarily focused on either approximate solutions, such as Bloom Filters, or exact methods, like perfect hashing and dictionaries, without attempting to develop an integral theory. In this paper, we propose a unified and complete theory, namely chain rule, for general membership problems, which encompasses both approximate and exact membership as extreme cases. Building upon the chain rule, we introduce a straightforward yet versatile algorithm framework, namely ChainedFilter, to combine different elementary filters without losing information. Our evaluation results demonstrate that ChainedFilter improves performance of many applications including static dictionary, lossless data compression, Cuckoo Hashing, LSM-Tree and Learned Filters.
- 8 December 2023
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Management of Data
- Vol. 1 (4) , 1-27
Open AccessChainedFilter: Combining Membership Filters by Chain Rule
Membership (membership query/membership testing) is a fundamental problem across databases, networks and security. However, previous research has primarily focused on either approximate solutions, such as Bloom Filters, or exact methods, like perfect hashing and dictionaries, without attempting to develop an integral theory. In this paper, we propose a unified and complete theory, namely chain rule, for general membership problems, which encompasses both approximate and exact membership as extreme cases. Building upon the chain rule, we introduce a straightforward yet versatile algorithm framework, namely ChainedFilter, to combine different elementary filters without losing information. Our evaluation results demonstrate that ChainedFilter improves performance of many applications including static dictionary, lossless data compression, Cuckoo Hashing, LSM-Tree and Learned Filters.
- Open Access
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 903-914
Equivariant Learning for Out-of-Distribution Cold-start Recommendation
Recommender systems rely on user-item interactions to learn Collaborative Filtering (CF) signals and easily under-recommend the cold-start items without historical interactions. To boost cold-start item recommendation, previous studies usually incorporate item features (e.g., micro-video content features) into CF models. They essentially align the feature representations of warm-start items with CF representations during training, and then adopt the feature representations of cold-start items to make recommendations. However, cold-start items might have feature distribution shifts from warm-start ones due to different upload times. As such, these cold-start item features fall into the underrepresented feature space, where their feature representations cannot align well with CF signals, causing poor cold-start recommendation. To combat item feature shifts, the key lies in pushing feature representation learning to well represent the shifted item features and align with the CF representations in the underrepresented feature space. To this end, we propose an equivariant learning framework, which aims to achieve equivariant alignment between item features, feature representations, and CF representations in the underrepresented feature space. Specifically, since cold-start items are unavailable for training, we interpolate the features and CF representations of two underrepresented warm items to simulate the feature shifts. The interpolated feature representations are then regulated to achieve equivariant alignment with the interpolated features and CF representations via three alignment losses. We instantiate the proposed framework on two competitive cold-start models, and empirical results on three datasets validate that the framework significantly improves cold-start recommendation.
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 903-914
Open AccessEquivariant Learning for Out-of-Distribution Cold-start Recommendation
Recommender systems rely on user-item interactions to learn Collaborative Filtering (CF) signals and easily under-recommend the cold-start items without historical interactions. To boost cold-start item recommendation, previous studies usually incorporate item features (e.g., micro-video content features) into CF models. They essentially align the feature representations of warm-start items with CF representations during training, and then adopt the feature representations of cold-start items to make recommendations. However, cold-start items might have feature distribution shifts from warm-start ones due to different upload times. As such, these cold-start item features fall into the underrepresented feature space, where their feature representations cannot align well with CF signals, causing poor cold-start recommendation. To combat item feature shifts, the key lies in pushing feature representation learning to well represent the shifted item features and align with the CF representations in the underrepresented feature space. To this end, we propose an equivariant learning framework, which aims to achieve equivariant alignment between item features, feature representations, and CF representations in the underrepresented feature space. Specifically, since cold-start items are unavailable for training, we interpolate the features and CF representations of two underrepresented warm items to simulate the feature shifts. The interpolated feature representations are then regulated to achieve equivariant alignment with the interpolated features and CF representations via three alignment losses. We instantiate the proposed framework on two competitive cold-start models, and empirical results on three datasets validate that the framework significantly improves cold-start recommendation.
- Open Access
- 18 August 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 42 (1) , 1-27
Causal Disentangled Recommendation against User Preference Shifts
Recommender systems easily face the issue of user preference shifts. User representations will become out-of-date and lead to inappropriate recommendations if user preference has shifted over time. To solve the issue, existing work focuses on learning robust representations or predicting the shifting pattern. There lacks a comprehensive view to discover the underlying reasons for user preference shifts. To understand the preference shift, we abstract a causal graph to describe the generation procedure of user interaction sequences. Assuming user preference is stable within a short period, we abstract the interaction sequence as a set of chronological environments. From the causal graph, we find that the changes of some unobserved factors (e.g., becoming pregnant) cause preference shifts between environments. Besides, the fine-grained user preference over item categories sparsely affects the interactions with different items. Inspired by the causal graph, our key considerations to handle preference shifts lie in modeling the interaction generation procedure by: 1) capturing the preference shifts across environments for accurate preference prediction, and 2) disentangling the sparse influence from user preference to interactions for accurate effect estimation of preference. To this end, we propose a Causal Disentangled Recommendation (CDR) framework, which captures preference shifts via a temporal variational autoencoder and learns the sparse influence from multiple environments. Specifically, an encoder is adopted to infer the unobserved factors from user interactions while a decoder is to model the interaction generation process. Besides, we introduce two learnable matrices to disentangle the sparse influence from user preference to interactions. Lastly, we devise a multi-objective loss to optimize CDR. Extensive experiments on three datasets show the superiority of CDR in enhancing the generalization ability under user preference shifts.
- 18 August 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 42 (1) , 1-27
Open AccessCausal Disentangled Recommendation against User Preference Shifts
Recommender systems easily face the issue of user preference shifts. User representations will become out-of-date and lead to inappropriate recommendations if user preference has shifted over time. To solve the issue, existing work focuses on learning robust representations or predicting the shifting pattern. There lacks a comprehensive view to discover the underlying reasons for user preference shifts. To understand the preference shift, we abstract a causal graph to describe the generation procedure of user interaction sequences. Assuming user preference is stable within a short period, we abstract the interaction sequence as a set of chronological environments. From the causal graph, we find that the changes of some unobserved factors (e.g., becoming pregnant) cause preference shifts between environments. Besides, the fine-grained user preference over item categories sparsely affects the interactions with different items. Inspired by the causal graph, our key considerations to handle preference shifts lie in modeling the interaction generation procedure by: 1) capturing the preference shifts across environments for accurate preference prediction, and 2) disentangling the sparse influence from user preference to interactions for accurate effect estimation of preference. To this end, we propose a Causal Disentangled Recommendation (CDR) framework, which captures preference shifts via a temporal variational autoencoder and learns the sparse influence from multiple environments. Specifically, an encoder is adopted to infer the unobserved factors from user interactions while a decoder is to model the interaction generation process. Besides, we introduce two learnable matrices to disentangle the sparse influence from user preference to interactions. Lastly, we devise a multi-objective loss to optimize CDR. Extensive experiments on three datasets show the superiority of CDR in enhancing the generalization ability under user preference shifts.
- Open Access
- 6 April 2020
- Published by Wolters Kluwer Health in International Journal of Dermatology and Venereology
- Vol. 3 (3) , 135-141
Chinese Expert Consensus on the Diagnosis and Management of Food Allergy in Children With Atopic Dermatitis#
The diagnosis of food allergy in clinical practice has not been standardized, and food allergy is overdiagnosed in patients with atopic dermatitis (AD). This overdiagnosis of food allergy leads to unnecessary elimination diets that may exert potential adverse effects on the health of children with AD. Unlike classic IgE-mediated food allergy, food allergy in patients with AD may manifest as non-eczematous reactions, isolated eczematous reactions, or a combination of these reactions. The diagnosis of food allergy in children with AD should be made based on a thorough clinical history (detailed allergic history and feeding history), clinical manifestations, and laboratory workup including skin prick testing, serum specific IgE measurement, atopy patch testing, and oral food challenges. Once an underlying food allergy is confirmed in a patient with AD, comprehensive management is generally recommended. Avoidance of the food allergen is the main treatment approach, but there is a need for regular clinical follow-up, including evaluation of the nutritional status and supervision of growth and development. Multidisciplinary cooperation between dermatologists, nutritionists, and pediatricians is required.
- 6 April 2020
- Published by Wolters Kluwer Health in International Journal of Dermatology and Venereology
- Vol. 3 (3) , 135-141
Open AccessChinese Expert Consensus on the Diagnosis and Management of Food Allergy in Children With Atopic Dermatitis#
The diagnosis of food allergy in clinical practice has not been standardized, and food allergy is overdiagnosed in patients with atopic dermatitis (AD). This overdiagnosis of food allergy leads to unnecessary elimination diets that may exert potential adverse effects on the health of children with AD. Unlike classic IgE-mediated food allergy, food allergy in patients with AD may manifest as non-eczematous reactions, isolated eczematous reactions, or a combination of these reactions. The diagnosis of food allergy in children with AD should be made based on a thorough clinical history (detailed allergic history and feeding history), clinical manifestations, and laboratory workup including skin prick testing, serum specific IgE measurement, atopy patch testing, and oral food challenges. Once an underlying food allergy is confirmed in a patient with AD, comprehensive management is generally recommended. Avoidance of the food allergen is the main treatment approach, but there is a need for regular clinical follow-up, including evaluation of the nutritional status and supervision of growth and development. Multidisciplinary cooperation between dermatologists, nutritionists, and pediatricians is required.