One-Shot Relation Learning for Knowledge Graphs via Neighborhood Aggregation and Paths Encoding

The relation learning between two entities is an essential task in knowledge graph (KG) completion that has received much attention recently. Previous work almost exclusively focused on relations widely seen in the original KGs, which means that enough training data are available for modeling. However, long-tail relations that only show in a few triples are actually much more common in practical KGs. Without sufficiently large training data, the performance of existing models on predicting long-tail relations drops impressively. This work aims to predict the relation under a challenging setting where only one instance is available for training. We propose a path-based one-shot relation prediction framework, which can extract neighborhood information of an entity based on the relation query attention mechanism to learn transferable knowledge among the same relation. Simultaneously, to reduce the impact of long-tail entities on relation prediction, we selectively fuse path information between entity pairs as auxiliary information of relation features. Experiments in three one-shot relation learning datasets show that our proposed framework substantially outperforms existing models on one-shot link prediction and relation prediction.

A Graph-Based Approach for Mitigating Multi-Sided Exposure Bias in Recommender Systems

Fairness is a critical system-level objective in recommender systems that has been the subject of extensive recent research. A specific form of fairness is supplier exposure fairness, where the objective is to ensure equitable coverage of items across all suppliers in recommendations provided to users. This is especially important in multistakeholder recommendation scenarios where it may be important to optimize utilities not just for the end user but also for other stakeholders such as item sellers or producers who desire a fair representation of their items. This type of supplier fairness is sometimes accomplished by attempting to increase aggregate diversity to mitigate popularity bias and to improve the coverage of long-tail items in recommendations. In this article, we introduce FairMatch, a general graph-based algorithm that works as a post-processing approach after recommendation generation to improve exposure fairness for items and suppliers. The algorithm iteratively adds high-quality items that have low visibility or items from suppliers with low exposure to the users’ final recommendation lists. A comprehensive set of experiments on two datasets and comparison with state-of-the-art baselines show that FairMatch, although it significantly improves exposure fairness and aggregate diversity, maintains an acceptable level of relevance of the recommendations.

Bilateral Filtering Graph Convolutional Network for Multi-relational Social Recommendation in the Power-law Networks

In recent years, advances in Graph Convolutional Networks (GCNs) have given new insights into the development of social recommendation. However, many existing GCN-based social recommendation methods often directly apply GCN to capture user-item and user-user interactions, which probably have two main limitations: (a) Due to the power-law property of the degree distribution, the vanilla GCN with static normalized adjacency matrix has limitations in learning node representations, especially for the long-tail nodes; (b) multi-typed social relationships between users that are ubiquitous in the real world are rarely considered. In this article, we propose a novel Bilateral Filtering Heterogeneous Attention Network (BFHAN), which improves long-tail node representations and leverages multi-typed social relationships between user nodes. First, we propose a novel graph convolutional filter for the user-item bipartite network and extend it to the user-user homogeneous network. Further, we theoretically analyze the correlation between the convergence values of different graph convolutional filters and node degrees after stacking multiple layers. Second, we model multi-relational social interactions between users as the multiplex network and further propose a multiplex attention network to capture distinctive inter-layer influences for user representations. Last but not least, the experimental results demonstrate that our proposed method outperforms several state-of-the-art GCN-based methods for social recommendation tasks.

Determining the Service Life Cycle of Computers

The logistic diffusion equation is modified in order to take into account the long tail seen in revenues from servicing computer products. The model is applied to computers of DEC (Digital equipment Corporation.)

Long Tail Leadership

The increased weighting of digital natives in a fattening long tail has added complexity to organizational leadership, particularly during the global COVID-19 pandemic. Trends affecting the individual come from social, economic, and technological sources and affect leadership behaviors, and this in turn affects society. In order to understand this interconnection, lower-level influences and how they affect the higher-level visible signs are discussed. These lead to influences on behavior. Influences are felt as intensity and embeddedness of engagement, decision-management, feedback ability, and motivators. This chapter begins with a discussion of causes for this phenomenon and concludes with ways to work with the long tail, either from within as a member or externally as a leader. The chapter ends with a brief comment on future research based on findings discussed in this chapter.

Low I/O Intensity-aware Partial GC Scheduling to Reduce Long-tail Latency in SSDs

This article proposes a low I/O intensity-aware scheduling scheme on garbage collection (GC) in SSDs for minimizing the I/O long-tail latency to ensure I/O responsiveness. The basic idea is to assemble partial GC operations by referring to several determinable factors (e.g., I/O characteristics) and dispatch them to be processed together in idle time slots of I/O processing. To this end, it first makes use of Fourier transform to explore the time slots having relative sparse I/O requests for conducting time-consuming GC operations, as the number of affected I/O requests can be limited. After that, it constructs a mathematical model to further figure out the types and quantities of partial GC operations, which are supposed to be dealt with in the explored idle time slots, by taking the factors of I/O intensity, read/write ratio, and the SSD use state into consideration. Through a series of simulation experiments based on several realistic disk traces, we illustrate that the proposed GC scheduling mechanism can noticeably reduce the long-tail latency by between 5.5% and 232.3% at the 99.99th percentile, in contrast to state-of-the-art methods.

The first sheep graph pan-genome reveals the spectrum of structural variations and their effects on different tail phenotypes

Structural variations (SVs) are a major contributor of genetic diversity and phenotypic variations, however their prevalence and functions in domestic animals are largely unexplored. Here, we assembled 26 haplotype-resolved genome assemblies from 13 genetically diverse sheep breeds using PacBio HiFi sequencing. We then constructed an ovine graph pan-genome and demonstrated its advantage in discovering 142,593 biallelic SVs (Insertions and deletions), 7,028 divergent alleles and 13,419 multiallelic variations with high accuracy and sensitivity. To link the SVs to genotypes, we genotyped the SVs in 687 resequenced individuals of domestic and wild sheep using a graph-based approach and identified numerous population-stratified variants, of which expression-associated SVs were detected by integrating RNA-seq data. Taking the varying sheep tail morphology as example, we located a putative causative insertion in HOXB13 gene responsible for the long tail and reported multiple large SVs associated with the fat tail. Beyond generating a benchmark resource for ovine structural variants, our study also highlighted that the population genetics analysis based on graph pan-genome rather than reference genome will greatly benefit the animal genetic research.

Hybrid Recommendation Scheme Based on Deep Learning

Big data has been developed for nearly a decade, and the information data on the network is exploding. Facing the complex and massive data, it is difficult for people to get the demanded information quickly, and the recommendation algorithm with its characteristics becomes one of the important methods to solve the massive data overload problem at this stage. In particular, the rise of the e-commerce industry has promoted the development of recommendation algorithms. Traditional, single recommendation algorithms often have problems such as cold start, data sparsity, and long-tail items. The hybrid recommendation algorithms at this stage can effectively avoid some of the drawbacks caused by a single algorithm. To address the current problems, this paper makes up for the shortcomings of a single collaborative model by proposing a hybrid recommendation algorithm based on deep learning IA-CN. The algorithm first uses an integrated strategy to fuse user-based and item-based collaborative filtering algorithms to generalize and classify the output results. Then deeper and more abstract nonlinear interactions between users and items are captured by improved deep learning techniques. Finally, we designed experiments to validate the algorithm. The experiments are compared with the benchmark algorithm on (Amazon item rating dataset), and the results show that the IA-CN algorithm proposed in this paper has better performance in rating prediction on the test dataset.

Evaluating Phage Tail Fiber Receptor-Binding Proteins Using a Luminescent Flow-Through 96-Well Plate Assay

Phages have demonstrated significant potential as therapeutics in bacterial disease control and as diagnostics due to their targeted bacterial host range. Host range has typically been defined by plaque assays; an important technique for therapeutic development that relies on the ability of a phage to form a plaque upon a lawn of monoculture bacteria. Plaque assays cannot be used to evaluate a phage’s ability to recognize and adsorb to a bacterial strain of interest if the infection process is thwarted post-adsorption or is temporally delayed, and it cannot highlight which phages have the strongest adsorption characteristics. Other techniques, such as classic adsorption assays, are required to define a phage’s “adsorptive host range.” The issue shared amongst all adsorption assays, however, is that they rely on the use of a complete bacteriophage and thus inherently describe when all adsorption-specific machinery is working together to facilitate bacterial surface adsorption. These techniques cannot be used to examine individual interactions between a singular set of a phage’s adsorptive machinery (like long tail fibers, short tail fibers, tail spikes, etc.) and that protein’s targeted bacterial surface receptor. To address this gap in knowledge we have developed a high-throughput, filtration-based, bacterial binding assay that can evaluate the adsorptive capability of an individual set of a phage’s adsorption machinery. In this manuscript, we used a fusion protein comprised of an N-terminal bioluminescent tag translationally fused to T4’s long tail fiber binding tip (gp37) to evaluate and quantify gp37’s relative adsorptive strength against the Escherichia coli reference collection (ECOR) panel of 72 Escherichia coli isolates. Gp37 could adsorb to 61 of the 72 ECOR strains (85%) but coliphage T4 only formed plaques on 8 of the 72 strains (11%). Overlaying these two datasets, we were able to identify ECOR strains incompatible with T4 due to failed adsorption, and strains T4 can adsorb to but is thwarted in replication at a step post-adsorption. While this manuscript only demonstrates our assay’s ability to characterize adsorptive capabilities of phage tail fibers, our assay could feasibly be modified to evaluate other adsorption-specific phage proteins.