HSRec: Hierarchical self-attention incorporating knowledge graph for sequential recommendation

Modeling user’s fine-grained preferences and dynamic preference evolution from their chronological behaviors are challenging and crucial for sequential recommendation. In this paper, we develop a Hierarchical Self-Attention Incorporating Knowledge Graph for Sequential Recommendation (HSRec). HSRec models not only the user’s intrinsic preferences but also the user’s external potential interests to capture the user’s fine-grained preferences. Specifically, the intrinsic interest module and potential interest module are designed to capture these two preferences respectively. In the intrinsic interest module, user’s sequential patterns are characterized from their behaviors via the self-attention mechanism. As for the potential interest module, high-order paths can be generated with the help of the knowledge graph. Therefore, a hierarchical self-attention mechanism is designed to aggregate the semantic information of user interaction from these paths. Specifically, an entity-level self-attention mechanism is applied to capture the sequential patterns contained in the high-order paths while an interaction-level self-attention mechanism is designed to further capture the semantic information from user interactions. Moreover, according to the high-order semantic relevance, HSRec can explore the user’s dynamic preferences at each time, thus describing the user’s dynamic preference evolution. Finally, experiments conducted on three real world datasets demonstrate the state-of-the-art performance of the HSRec.

Incorporating Memory-Based Preferences and Point-of-Interest Stickiness into Recommendations in Location-Based Social Networks

In location-based social networks (LBSNs), point-of-interest (POI) recommendations facilitate access to information for people by recommending attractive locations they have not previously visited. Check-in data and various contextual factors are widely taken into consideration to obtain people’s preferences regarding POIs in existing POI recommendation methods. In psychological effect-based POI recommendations, the memory-based attenuation of people’s preferences with respect to POIs, e.g., the fact that more attention is paid to POIs that were checked in to recently than those visited earlier, is emphasized. However, the memory effect only reflects the changes in an individual’s check-in trajectory and cannot discover the important POIs that dominate their mobility patterns, which are related to the repeat-visit frequency of an individual at a POI. To solve this problem, in this paper, we developed a novel POI recommendation framework using people’s memory-based preferences and POI stickiness, named U-CF-Memory-Stickiness. First, we used the memory-based preference-attenuation mechanism to emphasize personal psychological effects and memory-based preference evolution in human mobility patterns. Second, we took the visiting frequency of POIs into consideration and introduced the concept of POI stickiness to identify the important POIs that reflect the stable interests of an individual with respect to their mobility behavior decisions. Lastly, we incorporated the influence of both memory-based preferences and POI stickiness into a user-based collaborative filtering framework to improve the performance of POI recommendations. The results of the experiments we conducted on a real LBSN dataset demonstrated that our method outperformed other methods.

Visual mate preference evolution during butterfly speciation is linked to neural processing genes

Many animal species remain separate not because their individuals fail to produce viable hybrids but because they “choose” not to mate. However, we still know very little of the genetic mechanisms underlying changes in these mate preference behaviours. Heliconius butterflies display bright warning patterns, which they also use to recognize conspecifics. Here, we couple QTL for divergence in visual preference behaviours with population genomic and gene expression analyses of neural tissue (central brain, optic lobes and ommatidia) across development in two sympatric Heliconius species. Within a region containing 200 genes, we identify five genes that are strongly associated with divergent visual preferences. Three of these have previously been implicated in key components of neural signalling (specifically an ionotropic glutamate receptor and two regucalcins), and overall our candidates suggest shifts in behaviour involve changes in visual integration or processing. This would allow preference evolution without altering perception of the wider environment.

Evolution of individual preferences and persistence of family rules

How does the distribution of individual preferences evolve as a result of marriage between individuals with different preferences? Could a family rule be self-enforcing given individual preferences, and remain such for several generations despite preference evolution? We show that it is in a couple’s common interest to obey a rule requiring them to give specified amounts of attention to their elderly parents if the couple’s preferences satisfy a certain condition, and the same condition is rationally expected to hold also where their children and respective spouses are concerned. Given uncertainty about who their children will marry, a couple’s expectations will reflect the probability distribution of preferences in the next generation. We show that, in any given generation, some couples may obey the rule in question and some may not. It is also possible that a couple will obey the rule, but their descendants will not for a number of generations, and then obey it again. In the long run, if matching is entirely random, either everybody obeys the same rule, or nobody obeys any. If matching is restricted to particular subpopulations identifiable by some visible trait, such as religion or color of the skin, different subpopulations may obey different rules. The policy implications are briefly discussed.

Visual mate preference evolution during butterfly speciation is linked to neural processing genes

Many animal species remain separate not because they fail to produce viable hybrids, but because their individuals “choose” not to mate. However, we still know very little of the genetic mechanisms underlying changes in these mate preference behaviours. Heliconius butterflies display bright warning patterns, which they also use to recognize conspecifics. Here, we couple QTL for divergence in visual preference behaviours with population genomic and gene expression analyses of neural tissue (central brain, optic lobes and ommatidia) across development in two sympatric Heliconius species. Within a region containing 200 genes, we identify five genes that are strongly associated with divergent visual preferences. Three of these have previously been implicated in key components of neural signalling (specifically an ionotropic glutamate receptor and two regucalcins), and overall our candidates suggest shifts in behaviour involve changes in visual integration or processing. This would allow preference evolution without altering perception of the wider environment.

The Genetics of Male Pheromone Preference Difference Between Drosophila melanogaster and Drosophila simulans

Species of flies in the genus Drosophila differ dramatically in their preferences for mates, but little is known about the genetic or neurological underpinnings of this evolution. Recent advances have been made to our understanding of one case: pheromone preference evolution between the species D. melanogaster and D. simulans. Males of both species are very sensitive to the pheromone 7,11-HD that is present only on the cuticle of female D. melanogaster. In one species this cue activates courtship, and in the other it represses it. This change in valence was recently shown to result from the modification of central processing neurons, rather than changes in peripherally expressed receptors, but nothing is known about the genetic changes that are responsible. In the current study, we show that a 1.35 Mb locus on the X chromosome has a major effect on male 7,11-HD preference. Unfortunately, when this locus is divided, the effect is largely lost. We instead attempt to filter the 159 genes within this region using our newfound understanding of the neuronal underpinnings of this phenotype to identify and test candidate genes. We present the results of these tests, and discuss the difficulty of identifying the genetic architecture of behavioral traits and the potential of connecting these genetic changes to the neuronal modifications that elicit different behaviors.