A Reinforcement Learning Framework for Explainable Recommendation

Wang, Xiting; Chen, Yiru; Ye, Jie; Wu, Le; Wu, Zhengtao; Xie, Xing

doi:10.1109/icdm.2018.00074

Cited by 118 publications

(75 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Note that due to the table space this is an incomplete enumeration of the existing explainable recommendation methods, and more methods are introduced in detail in the following parts of the survey. Besides, some of the table cells are empty because to the best of our knowledge there has not been a work falling into the corresponding combination User or item features Vig et al, 2009Zhang et al, 2014a McAuley and Leskovec, 2013 He et al, 2015Seo et al, 2017Huang et al, 2018Davidson et al, 2010McInerney et al, 2018 Textual sentence explanation Zhang et al, 2014aLi et al, 2017Ai et al, 2018Balog et al, 2019Wang et al, 2018d Visual explanation et al, 2019b research according to this taxonomy, so that readers can understand the relationship between existing explainable recommendation methods. Due to the large body of related work, Table 1.1 is only an incomplete enumeration of explainable recommendation methods.…”

Section: A Historical Overviewmentioning

confidence: 99%

“…The version of record is available at: http://dx.doi.org/10.1561/1500000066 Figure 3.13: A reinforcement learning framework for generating recommendation explanations. The coupled agents learn to select the explanations that best approximate the predictions made by the recommendation model (Wang et al, 2018d). of ranking models.…”

Section: Model Agnostic and Post Hoc Explainable Recommendationmentioning

confidence: 99%

See 1 more Smart Citation

Explainable Recommendation: A Survey and New Perspectives

Zhang

Chen

2020

FNT in Information Retrieval

521

241

View full text Add to dashboard Cite

Explainable recommendation attempts to develop models that generate not only high-quality recommendations but also intuitive explanations. The explanations may either be post-hoc or directly come from an explainable model (also called interpretable or transparent model in some contexts). Explainable recommendation tries to address the problem of why: by providing explanations to users or system designers, it helps humans to understand why certain items are recommended by the algorithm, where the human can either be users or system designers. Explainable recommendation helps to improve the transparency, persuasiveness, effectiveness, trustworthiness, and satisfaction of recommendation systems. It also facilitates system designers for better system debugging. In recent years, a large number of explainable recommendation approaches -especially model-based methods -have been proposed and applied in real-world systems.In this survey, we provide a comprehensive review for the explainable recommendation research. We first highlight the position of explainable recommendation in recommender system research by categorizing recommendation problems into the 5W, i.e., what, when, who, where, and why. We then conduct a comprehensive survey of explainable recommendation on three perspectives: 1) We provide a chronological research timeline of explainable recommendation, including user study approaches in the early years and more recent model-based approaches. 2) We provide a two-dimensional taxonomy to classify existing explainable recommendation research: one dimension is the information source (or display style) of the explanations, and the other dimension is the algorithmic mechanism to generate explainable recommendations. 3) We summarize how explainable recommendation applies to different recommendation tasks, such as product recommendation, social recommendation, and POI recommendation.We also devote a section to discuss the explanation perspectives in broader IR and AI/ML research. We end the survey by discussing potential future directions to promote the explainable recommendation research area and beyond.Explainable recommendation refers to personalized recommendation algorithms that address the problem of why -they not only provide users or system designers with recommendation results, but also explanations to clarify why such items are recommended. In this way, it helps to improve the transparency, persuasiveness, effectiveness, trustworthiness, and user satisfaction of the recommendation systems. It also facilitates system designers to diagnose, debug, and refine the recommendation algorithm.To highlight the position of explainable recommendation in the recommender system research area, we classify personalized recommendation with a broad conceptual taxonomy. Specifically, personalized recommendation research can be classified into the 5W problemswhen, where, who, what, and why, corresponding to time-aware recommendation (when), location-based recommendation (where), social recommendation (who), application-aware re...

show abstract

Section: A Historical Overviewmentioning

confidence: 99%

Section: Model Agnostic and Post Hoc Explainable Recommendationmentioning

confidence: 99%

Explainable Recommendation: A Survey and New Perspectives

Zhang

Chen

2020

FNT in Information Retrieval

521

241

View full text Add to dashboard Cite

show abstract

“…Recently, researchers have discovered that providing explanations may improve persuasiveness, effectiveness, efficiency and user trust (Zhang et al 2014a). Thus, many methods have been developed to improve the explainability of recommendation models (Ren et al 2017;Peake and Wang 2018;Wang et al 2018b). Pioneer works (McAuley and Leskovec 2013;Zhang et al 2014a) focus on improving the explainability of collaborative filtering models.…”

Section: Related Workmentioning

confidence: 99%

Explainable Recommendation through Attentive Multi-View Learning

Gao

Wang

et al. 2019

AAAI

Self Cite

View full text Add to dashboard Cite

Recommender systems have been playing an increasingly important role in our daily life due to the explosive growth of information. Accuracy and explainability are two core aspects when we evaluate a recommendation model and have become one of the fundamental trade-offs in machine learning. In this paper, we propose to alleviate the trade-off between accuracy and explainability by developing an explainable deep model that combines the advantages of deep learning-based models and existing explainable methods. The basic idea is to build an initial network based on an explainable deep hierarchy (e.g., Microsoft Concept Graph) and improve the model accuracy by optimizing key variables in the hierarchy (e.g., node importance and relevance). To ensure accurate rating prediction, we propose an attentive multi-view learning framework. The framework enables us to handle sparse and noisy data by co-regularizing among different feature levels and combining predictions attentively. To mine readable explanations from the hierarchy, we formulate personalized explanation generation as a constrained tree node selection problem and propose a dynamic programming algorithm to solve it. Experimental results show that our model outperforms state-of-the-art methods in terms of both accuracy and explainability.

show abstract

“…However, we may use a narrative of the algorithm to exchange for understandability, as seen in Figure 7. The idea of TA in EML is imitated by a reinforcement framework proposed by Wang et al (2018). Sometimes, the machine learning algorithm is too complex to be thoroughly grasped.…”

Section: Design Of a Prototypical DL Systemmentioning

confidence: 99%

On the Logical Design of a Prototypical Data Lake System for Biological Resources

Che

Duan

2020

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

Biological resources are multifarious encompassing organisms, genetic materials, populations, or any other biotic components of ecosystems, and fine-grained data management and processing of these diverse types of resources proposes a tremendous challenge for both researchers and practitioners. Before the conceptualization of data lakes, former big data management platforms in the research fields of computational biology and biomedicine could not deal with many practical data management tasks very well. As an effective complement to those previous systems, data lakes were devised to store voluminous, varied, and diversely structured or unstructured data in their native formats, for the sake of various analyses like reporting, modeling, data exploration, knowledge discovery, data visualization, advanced analysis, and machine learning. Due to their intrinsic traits, data lakes are thought to be ideal technologies for processing of hybrid biological resources in the format of text, image, audio, video, and structured tabular data. This paper proposes a method for constructing a practical data lake system for processing multimodal biological data using a prototype system named ProtoDLS, especially from the explainability point of view, which is indispensable to the rigor, transparency, persuasiveness, and trustworthiness of the applications in the field. ProtoDLS adopts a horizontal pipeline to ensure the intra-component explainability factors from data acquisition to data presentation, and a vertical pipeline to ensure the inner-component explainability factors including mathematics, algorithm, execution time, memory consumption, network latency, security, and sampling size. The dual mechanism can ensure the explainability guarantees on the entirety of the data lake system. ProtoDLS proves that a single point of explainability cannot thoroughly expound the cause and effect of the matter from an overall perspective, and adopting a systematic, dynamic, and multisided way of thinking and a system-oriented analysis method is critical when designing a data processing system for biological resources.

show abstract

A Reinforcement Learning Framework for Explainable Recommendation

Cited by 118 publications

References 21 publications

Explainable Recommendation: A Survey and New Perspectives

Explainable Recommendation: A Survey and New Perspectives

Explainable Recommendation through Attentive Multi-View Learning

On the Logical Design of a Prototypical Data Lake System for Biological Resources

Contact Info

Product

Resources

About