Top-N sequential recommendation models each user as a sequence of items interacted in the past and aims to predict top-N ranked items that a user will likely interact in a "near future". The order of interaction implies that sequential patterns play an important role where more recent items in a sequence have a larger impact on the next item. In this paper, we propose a Convolutional Sequence Embedding Recommendation Model (Caser) as a solution to address this requirement. The idea is to embed a sequence of recent items into an "image" in the time and latent spaces and learn sequential patterns as local features of the image using convolutional lters. This approach provides a uni ed and exible network structure for capturing both general preferences and sequential patterns. The experiments on public data sets demonstrated that Caser consistently outperforms state-of-the-art sequential recommendation methods on a variety of common evaluation metrics.
Pesticide trapping efficiency of vegetated filter strips (VFS) is commonly predicted with low success using empirical equations based solely on physical characteristics such as width and slope. The objective of this research was to develop and evaluate an empirical model with a foundation of VFS hydrological, sedimentological, and chemical specific parameters. The literature was reviewed to pool data from five studies with hypothesized significant parameters: pesticide and soil properties, percent reduction in runoff volume (i.e., infiltration) and sedimentation, and filter strip width. The empirical model was constructed using a phase distribution parameter, defined as the ratio of pesticide mass in dissolved form to pesticide mass sorbed to sediment, along with the percent infiltration, percent sedimentation, and the percent clay content (R(2) = 0.86 and standard deviation of differences [STDD] of 7.8%). Filter strip width was not a statistically significant parameter in the empirical model. For low to moderately sorbing pesticides, the phase distribution factor became statistically insignificant; for highly sorbing pesticides, the phase distribution factor became the most statistically significant parameter. For independent model evaluation datasets, the empirical model based on infiltration and sediment reduction, the phase distribution factor, and the percent clay content (STDD of 14.5%) outperformed existing filter strip width equations (STDD of 38.7%). This research proposed a procedure linking a VFS hydrologic simulation model with the proposed empirical trapping efficiency equation. For datasets with sufficient information for the VFS modeling, the linked numerical and empirical models significantly (R(2) = 0.74) improved predictions of pesticide trapping over empirical equations based solely on physical VFS characteristics.
Understanding temporal dynamics has proved to be highly valuable for accurate recommendation. Sequential recommenders have been successful in modeling the dynamics of users and items over time.However, while different model architectures excel at capturing various temporal ranges or dynamics, distinct application contexts require adapting to diverse behaviors.In this paper we examine how to build a model that can make use of different temporal ranges and dynamics depending on the request context. We begin with the analysis of an anonymized Youtube dataset comprising millions of user sequences. We quantify the degree of long-range dependence in these sequences and demonstrate that both short-term and long-term dependent behavioral patterns co-exist. We then propose a neural Multi-temporalrange Mixture Model (M3) as a tailored solution to deal with both short-term and long-term dependencies. Our approach employs a mixture of models, each with a different temporal range. These models are combined by a learned gating mechanism capable of exerting different model combinations given different contextual information. In empirical evaluations on a public dataset and our own anonymized YouTube dataset, M3 consistently outperforms state-of-the-art sequential recommendation methods.
Recommender systems play an important role in modern information and e-commerce applications. While increasing research is dedicated to improving the relevance and diversity of the recommendations, the potential risks of state-of-the-art recommendation models are under-explored, that is, these models could be subject to attacks from malicious third parties, through injecting fake user interactions to achieve their purposes. This paper revisits the adversarially-learned injection attack problem, where the injected fake user 'behaviors' are learned locally by the attackers with their own model-one that is potentially different from the model under attack, but shares similar properties to allow attack transfer. We found that most existing works in literature suffer from two major limitations: (1) they do not solve the optimization problem precisely, making the attack less harmful than it could be, (2) they assume perfect knowledge for the attack, causing the lack of understanding for realistic attack capabilities. We demonstrate that the exact solution for generating fake users as an optimization problem could lead to a much larger impact. Our experiments on a real-world dataset reveal important properties of the attack, including attack transferability and its limitations. These findings can inspire useful defensive methods against this possible existing attack. CCS CONCEPTS • Information systems → Recommender systems; • Security and privacy → Web application security.
Bamaxiang pig is from Guangxi province in China, characterized by its small body size and two‐end black coat colour. It is an important indigenous breed for local pork market and excellent animal model for biomedical research. In this study, we performed genomewide association studies (GWAS) on 43 growth and carcass traits in 315 purebred Bamaxiang pigs based on a 1.4 million SNP array. We observed considerable phenotypic variability in the growth and carcass traits in the Bamaxiang pigs. The corresponding SNP based heritability varied greatly across the 43 traits and ranged from 9.0% to 88%. Through a conditional GWAS, we identified 53 significant associations for 35 traits at p value threshold of 10−6. Among which, 26 associations on chromosome 3, 7, 14 and X passed a genomewide significance threshold of 5 × 10−8. The most remarkable loci were at around 30.6 Mb on chromosome 7, which had growth stage‐dependent effects on body lengths and cannon circumferences and showed large effects on multiple carcass traits. We discussed HMGA1 NUDT3, EIF2AK1, TMEM132C and AFF2 that near the lead SNP of significant loci as plausible candidate genes for corresponding traits. We also showed that including phenotypic covariate in GWAS can help to reveal additional significant loci for the target traits. The results provide insight into the genetic architecture of growth and carcass traits in Bamaxiang pigs.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.