Multi-modal Knowledge-aware Reinforcement Learning Network for Explainable Recommendation

Liu

et al. 2021

Preprint

Recommender systems have been widely applied in different real-life scenarios to help us find useful information. Recently, Reinforcement Learning (RL) based recommender systems have become an emerging research topic. It often surpasses traditional recommendation models even most deep learning-based methods, owing to its interactive nature and autonomous learning ability. Nevertheless, there are various challenges of RL when applying in recommender systems. Toward this end, we firstly provide a thorough overview, comparisons, and summarization of RL approaches for five typical recommendation scenarios, following three main categories of RL: value-function, policy search, and Actor-Critic. Then, we systematically analyze the challenges and relevant solutions on the basis of existing literature. Finally, under discussion for open issues of RL and its limitations of recommendation, we highlight some potential research directions in this field.

Section: Recommender Scenarios Models Rl Algorithms Evaluation Methodsmentioning

confidence: 99%

A Survey on Reinforcement Learning for Recommender Systems

Liu

et al. 2021

Preprint

“…Some other approaches find other ways to utilize MMKG for more personalized and explainable recommendations. For instance, [168] fully exploits the graph structure of MMKG and designs a novel approach hierarchy attention-path over MMKGs for the reasoning over items with information across different modalities. Rich path semantics could be learned through entities and images within the path in MMKG, thus producing an interpretable and explicit recommendation with higher knowledge level.Differently, some recent efforts [131], [168] novelly proposes to construct a personalized MMKG from the images and texts of items in various ways, and then the entity relation reasoning between items can be better modeled by taking the relations in MMKG into account.…”

Section: Multi-modal Recommender Systemmentioning

confidence: 99%

Multi-Modal Knowledge Graph Construction and Application: A Survey

Zhu¹,

Li²,

Wang³

et al. 2022

Preprint

Recent years have witnessed the resurgence of knowledge engineering which is featured by the fast growth of knowledge graphs. However, most of existing knowledge graphs are represented with pure symbols, which hurts the machine's capability to understand the real world. The multi-modalization of knowledge graphs is an inevitable key step towards the realization of human-level machine intelligence. The results of this endeavor are Multi-modal Knowledge Graphs (MMKGs). In this survey on MMKGs constructed by texts and images, we first give definitions of MMKGs, followed with the preliminaries on multi-modal tasks and techniques. We then systematically review the challenges, progresses and opportunities on the construction and application of MMKGs respectively, with detailed analyses of the strength and weakness of different solutions. We finalize this survey with open research problems relevant to MMKGs.

“…if you want to observe each definition of 3-dimensional records and the definition of a commercial enterprise and a good way to address a meaningless scenario, we endorse the forms of commercial enterprise displays, structure-based presentation and definition-primarily based displays (Tao et al, 2021). We examine the totally display the carry out three intense as tons as knowledge graph in statistics, whilst descriptive reports do better with capturing textual facts in enterprise descriptions.…”

Section: Approachmentioning

confidence: 99%

“…We examine the totally display the carry out three intense as tons as knowledge graph in statistics, whilst descriptive reports do better with capturing textual facts in enterprise descriptions. We examine two commercial enterprise shows concurrently within the equal vector non-stop method, but do not force the shows to be blended to don't forget the potential to better represent (Tao et al, 2021). The description embodied knowledge representing learning is function is then described as 𝐸 = 𝐸 𝐷 + 𝐸 𝐺…”

Section: Approachmentioning

confidence: 99%

Learning of Knowledge Graphs with Entity Descriptions

Conde¹

2022

IJMRA

The representing learning makes specialty of knowledge graph and it indicates the difference between different entities. The knowledge graph representing with the low-dimensional space. In fact, most of the method usually concern of description of entity which is hard for existing strategies to take benefit of. Here, we recommend a new representing learning method with knowledge graphs that uses entity description. We evaluate our method on two tasks like knowledge graph and entity classification. Experimental effects on actual-world datasets show that our version plays higher than different baseline fashions, especially under the zero-short setting, which indicate that our technique for novel the entity description.