Search

Recommender systems are influenced by many confounding factors (i.e., confounders) which result in various biases (e.g., popularity biases) and inaccurate user preference. Existing approaches try to eliminate these biases by inference with causal graphs. However, they assume all confounding factors can be observed and no hidden confounders exist. We argue that many confounding factors (e.g., season) may not be observable from user–item interaction data, resulting inaccurate user preference. In this article, we propose a deconfounded recommender considering unobservable confounders. Specifically, we propose a new causal graph with explicit and implicit feedback, which can better model user preference. Then, we realize a deconfounded estimator by the front-door adjustment, which is able to eliminate the effect of unobserved confounders. Finally, we conduct a series of experiments on two real-world datasets, and the results show that our approach performs better than other counterparts in terms of recommendation accuracy. [ABSTRACT FROM AUTHOR]

Multi-scenario and multi-task recommendation can use various feedback behaviors of users in different scenarios to learn users' preferences and then make recommendations, which has attracted attention. However, the existing work ignores feature interactions and the fact that a pair of feature interactions will have differing levels of importance under different scenario-task pairs, leading to sub-optimal user preference learning. In this article, we propose a Multi-scenario and Multi-task aware Feature Interaction model, dubbed MMFI, to explicitly model feature interactions and learn the importance of feature interaction pairs in different scenarios and tasks. Specifically, MMFI first incorporates a pairwise feature interaction unit and a scenario-task interaction unit to effectively capture the interaction of feature pairs and scenario-task pairs. Then MMFI designs a scenario-task aware attention layer for learning the importance of feature interactions from coarse-grained to fine-grained, improving the model's performance on various scenario-task pairs. More specifically, this attention layer consists of three modules: a fully shared bottom module, a partially shared middle module, and a specific output module. Finally, MMFI adapts two sparsity-aware functions to remove some useless feature interactions. Extensive experiments on two public datasets demonstrate the superiority of the proposed method over the existing multi-task recommendation, multi-scenario recommendation, and multi-scenario & multi-task recommendation models. [ABSTRACT FROM AUTHOR]

High-throughput DNA sequencing technologies decode tremendous amounts of microbial protein-coding gene sequences. However, accurately assigning protein functions to novel gene sequences remain a challenge. To this end, we developed FunGeneTyper, an extensible framework with two new deep learning models (i.e. FunTrans and FunRep), structured databases, and supporting resources for achieving highly accurate (Accuracy > 0.99, F1-score > 0.97) and fine-grained classification of antibiotic resistance genes (ARGs) and virulence factor genes. Using an experimentally confirmed dataset of ARGs comprising remote homologous sequences as the test set, our framework achieves by-far-the-best performance in the discovery of new ARGs from human gut (F1-score: 0.6948), wastewater (0.6072), and soil (0.5445) microbiomes, beating the state-of-the-art bioinformatics tools and sequence alignment-based (F1-score: 0.0556–0.5065) and domain-based (F1-score: 0.2630–0.5224) annotation approaches. Furthermore, our framework is implemented as a lightweight, privacy-preserving, and plug-and-play neural network module, facilitating its versatility and accessibility to developers and users worldwide. We anticipate widespread utilization of FunGeneTyper (https://github.com/emblab-westlake/FunGeneTyper) for precise classification of protein-coding gene functions and the discovery of numerous valuable enzymes. This advancement will have a significant impact on various fields, including microbiome research, biotechnology, metagenomics, and bioinformatics. [ABSTRACT FROM AUTHOR]

Generative adversarial networks (GANs) have achieved a big success in collaborative filtering (CF). However, existing GAN-based methods in CF still suffer from the high-sparsity and cold-start problems; in addition, they also undergo the issues of excessive space complexity or inadequate training. In this article, we propose path2rec a novel adversarial path-based recommendation model to address these limitations of existing GAN-based methods in recommendation task by naturally incorporating auxiliary information (e.g., social networks and item attributes). It is composed of two modules, 1) pathGAN and 2) path2vec. In pathGAN, we consider both explicit and implicit friends, as well as item attributes by regarding them as the source of graph construction. Then, we propose a smart walk strategy to automatically generate an optimizing path, which can effectively learn the semantic distribution of users and items. In path2vec, to fully exploit context features of the generated path, we use the Continuous Bag of Words (CBOW) model to fine-tune nodes representations learned by pathGAN. Through extensive experiments on real-world datasets, we demonstrate the effectiveness of the proposed path2rec by applying it into top-n item recommendation, which reaches better performance than other counterparts. [ABSTRACT FROM AUTHOR]

The visual semantic embedding (VSE) aims to construct a joint embedding space between visual features and semantic information, whereby classes can be well retrieved for a given image. However, VSE faces the computational challenge due to the large scale image-class data and the constrained system processing power. To speed up model training, many researchers resort to different sampling strategies by involving only a small portion of the classes at each training step. However, these methods are greatly biased especially when the sampling distribution deviates from the true data distribution. In order to retain VSE models fidelity, we adopt the regular full-sample in our algorithm. We also devise two separate optimization strategies to reduce time complexity, and derive more effective updating rules. The experimental results on four real datasets demonstrate that our approach not only converges much faster than the state-of-the-art sampling models, but also generates more accurate class retrieval. [ABSTRACT FROM AUTHOR]

Data sparsity is a well-recognized issue for Top-N item recommendation, which depends on user preference gathered from their historical behaviors (i.e., implicit feedback). However, only few works have considered multiple types of auxiliary implicit feedback (e.g, click, wanted) when building recommendation models. This paper aims to resolve the data sparsity problem by (a) generating target data (e.g., purchase) from a linear regression of auxiliary feedback, and from the nearest neighbors with a set of purchased items in multiple dimensions; (b) proposing a novel ranking model to accommodate both the original and generated data. We provide an intuitive comprehension regarding the relationship between one kind of auxiliary feedback and target feedback. A series of experiments are conducted on two real-world datasets and demonstrate the superiority of our approach to other counterparts. [ABSTRACT FROM AUTHOR]

Nowadays, providing high-quality recommendation services to users is an essential component in web applications, including shopping, making friends, and healthcare. This can be regarded either as a problem of estimating users’ preference by exploiting explicit feedbacks (numerical ratings), or as a problem of collaborative ranking with implicit feedback (e.g., purchases, views, and clicks). Previous works for solving this issue include pointwise regression methods and pairwise ranking methods. The emerging healthcare websites and online medical databases impose a new challenge for medical service recommendation. In this paper, we develop a model, MBPR (Medical Bayesian Personalized Ranking over multiple users’ actions), based on the simple observation that users tend to assign higher ranks to some kind of healthcare services that are meanwhile preferred in users’ other actions. Experimental results on the real-world datasets demonstrate that MBPR achieves more accurate recommendations than several state-of-the-art methods and shows its generality and scalability via experiments on the datasets from one mobile shopping app. [ABSTRACT FROM AUTHOR]

Web service composition is a process to compose homogenous or heterogeneous services together in order to create value-added services. Many non-functional features including QoS and user preferences have been adopted to guide such a process. However, two issues are observed: (1) the expressiveness of user preference is subject to quantitative preferences without proper use of qualitative preferences; (2) a highly preferred composite service may not be trustworthy, or a highly trustworthy composite service may not be preferable. The existing studies concentrate on either user preference or service trust, and fail to provide a systematic solution to integrate both user preference and service trust together for service compositions. To address these issues, we combine both qualitative and quantitative preferences as well as service trust together in the process of service composition. We investigate the application of heuristic algorithms on multi-objective optimization for the service composition problem. A new hybrid nature inspired intelligent algorithm is also proposed and compared with other popular heuristic algorithms. We aim to obtain optimal web service compositions that can satisfy these (potentially conflicting) constraints as much as possible. Results demonstrate the efficiency and effectiveness of our approach in comparison with other counterparts. [ABSTRACT FROM PUBLISHER]

Trust-aware recommender systems have attracted much attention recently due to the prevalence of social networks. However, most existing trust-based approaches are designed for the recommendation task of rating prediction . Only few trust-aware methods have attempted to recommend users an ordered list of interesting items, i.e., item recommendation . In this article, we propose three factored similarity models with the incorporation of social trust for item recommendation based on implicit user feedback. Specifically, we introduce a matrix factorization technique to recover user preferences between rated items and unrated ones in the light of both user-user and item-item similarities. In addition, we claim that social trust relationships also have an important impact on a user’s preference for a specific item. Experimental results on three real-world data sets demonstrate that our approach achieves superior ranking performance to other counterparts. [ABSTRACT FROM AUTHOR]

We propose TrustSVD, a trust-based matrix factorization technique for recommendations. TrustSVD integrates multiple information sources into the recommendation model in order to reduce the data sparsity and cold start problems and their degradation of recommendation performance. An analysis of social trust data from four real-world data sets suggests that not only the explicit but also the implicit influence of both ratings and trust should be taken into consideration in a recommendation model. TrustSVD therefore builds on top of a state-of-the-art recommendation algorithm, SVD++ (which uses the explicit and implicit influence of rated items), by further incorporating both the explicit and implicit influence of trusted and trusting users on the prediction of items for an active user. The proposed technique is the first to extend SVD++ with social trust information. Experimental results on the four data sets demonstrate that TrustSVD achieves better accuracy than other ten counterparts recommendation techniques. [ABSTRACT FROM PUBLISHER]

Continual learning (CL) aims to learn new tasks without forgetting previous tasks. However, existing CL methods require a large amount of raw data, which is often unavailable due to copyright considerations and privacy risks. Instead, stakeholders usually release pre-trained machine learning models as a service (MLaaS), which users can access via APIs. This paper considers two practical-yet-novel CL settings: data-efficient CL (DECL-APIs) and data-free CL (DFCL-APIs), which achieve CL from a stream of APIs with partial or no raw data. Performing CL under these two new settings faces several challenges: unavailable full raw data, unknown model parameters, heterogeneous models of arbitrary architecture and scale, and catastrophic forgetting of previous APIs. To overcome these issues, we propose a novel data-free cooperative continual distillation learning framework that distills knowledge from a stream of APIs into a CL model by generating pseudo data, just by querying APIs. Specifically, our framework includes two cooperative generators and one CL model, forming their training as an adversarial game. We first use the CL model and the current API as fixed discriminators to train generators via a derivative-free method. Generators adversarially generate hard and diverse synthetic data to maximize the response gap between the CL model and the API. Next, we train the CL model by minimizing the gap between the responses of the CL model and the black-box API on synthetic data, to transfer the API's knowledge to the CL model. Furthermore, we propose a new regularization term based on network similarity to prevent catastrophic forgetting of previous APIs. Our method performs comparably to classic CL with full raw data on the MNIST and SVHN datasets in the DFCL-APIs setting. In the DECL-APIs setting, our method achieves 0.97×, 0.75× and 0.69× performance of classic CL on the more challenging CIFAR10, CIFAR100, and MiniImageNet, respectively.