Embedding Taxonomical, Situational or Sequential Knowledge Graph Context for Recommendation Tasks

Abstract

Learned latent vector representations are key to the success of many recommender systems in recent years. However, traditional approaches like matrix factorization produce vector representations that capture global distributions of a static recommendation scenario only. Such latent user or item representations do not capture background knowledge and are not customized to a concrete situational context and the sequential history of events leading up to it. This is a fundamentally limiting restriction for many tasks and applications, since the latent state can depend on a) abstract background information, b) the current situational context and c) the history of related observations. An illustrating example is a restaurant recommendation scenario, where a user’s assessment of the situation depends a) on taxonomical information regarding the type of cuisine, b) on situational factors like time of day, weather or location and c) on the subjective individual history and experience of this user in preceding situations. This situation-specific internal state of the user is not captured when using a traditional collaborative filtering approach, since background knowledge, the situational context and the sequential nature of an individual’s history cannot easily be represented in the matrix. In this paper, we investigate how well state-of-the-art approaches do exploit those different dimensions relevant to POI recommendation tasks. Naturally, we represent such a scenario as a temporal knowledge graph and compare plain knowledge graph, a taxonomy and a hypergraph embedding approach, as well as a recurrent neural network architecture to exploit the different context-dimensions of such rich information. Our empirical evidence indicates that the situational context is most crucial to the prediction performance, while the taxonomical and sequential information are harder to exploit. However, they still have their specific merits depending on the situation.

A Survey on Knowledge Graph-based Methods for Automated Driving

“…[56,15] Map representation [98] Decision making [87] Context learning [112] Map integration [84] Rules [117,115,116] KG-scene-graphs [114,34] Map updating [85] Reasoning [48,113] KG-based detection [110] Quality of maps [86] Rule learning [19,47,77] Common-sense [17] Scene understanding KG from text [22] Road sign recog. [59,76] Context model [107] Validation Lane detection [72,46] Situation understanding [38] Risk assessm. [9,81,109] Segmentation Behavior Prediction Test gener.…”

“…Scene understanding aims to understand what is happening in the scene, the relations between the objects in order to obtain a comprehension for further steps in automated driving that deal with motion planning and vehicle control. An approach for KG-based scene understanding was described by Werner et al [107]. The paper proposes a KG to model temporally contextualized observations and Recurrent Transformers (RETRA), a neural encoder stack with a feedback loop and constrained multi-headed self-attention layers.…”