18 August 2023 in ACM Transactions on Information Systems
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 User representations will become out-of-date and lead to inappropriate recommendations if user preference has shifted over time.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.
8 December 2023 in Proceedings of the ACM on Management of Data
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.
6 April 2020 in International Journal of Dermatology and Venereology
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.