https://cyberleninka.org/article/n/325149.pdf

Reference Architecture and Classification of Technologies, Products and Services for Big Data Systems

The use of large-scale data mining and machine learning has proliferated through the adoption of technologies such as Hadoop, with its simple programming semantics and rich and active ecosystem. This paper presents LinkedIn's Hadoop-based analytics stack, which allows data scientists and machine learning researchers to extract insights and build product features from massive amounts of data. In particular, we present our solutions to the ``last mile'' issues in providing a rich developer ecosystem. This includes easy ingress from and egress to online systems, and managing workflows as production processes. A key characteristic of our solution is that these distributed system concerns are completely abstracted away from researchers. For example, deploying data back into the online system is simply a 1-line Pig command that a data scientist can add to the end of their script. We also present case studies on how this ecosystem is used to solve problems ranging from recommendations to news feed updates to email digesting to descriptive analytical dashboards for our members.

/pdf/the-big-data-ecosystem-at-linkedin-3ixeik0qwq.pdf

The big data ecosystem at LinkedIn

Recommender Systems are nowadays successfully used by all major web sites—from e-commerce to social media—to filter content and make suggestions in a personalized way. Academic research largely focuses on the value of recommenders for consumers, e.g., in terms of reduced information overload. To what extent and in which ways recommender systems create business value is, however, much less clear, and the literature on the topic is scattered. In this research commentary, we review existing publications on field tests of recommender systems and report which business-related performance measures were used in such real-world deployments. We summarize common challenges of measuring the business value in practice and critically discuss the value of algorithmic improvements and offline experiments as commonly done in academic environments. Overall, our review indicates that various open questions remain both regarding the realistic quantification of the business effects of recommenders and the performance assessment of recommendation algorithms in academia.

Measuring the Business Value of Recommender Systems

I present a hybrid matrix factorisation model representing users and items as linear combinations of their content features’ latent factors. The model outperforms both collaborative and content-based models in cold-start or sparse interaction data scenarios (using both user and item metadata), and performs at least as well as a pure collaborative matrix factorisation model where interaction data is abundant. Additionally, feature embeddings produced by the model encode semantic information in a way reminiscent of word embedding approaches, making them useful for a range of related tasks such as tag recommendations.

/pdf/metadata-embeddings-for-user-and-item-cold-start-25g9gm4fls.pdf

Metadata Embeddings for User and Item Cold-start Recommendations

Recommender Systems are nowadays successfully used by all major web sites (from e-commerce to social media) to filter content and make suggestions in a personalized way. Academic research largely focuses on the value of recommenders for consumers, e.g., in terms of reduced information overload. To what extent and in which ways recommender systems create business value is, however, much less clear, and the literature on the topic is scattered. In this research commentary, we review existing publications on field tests of recommender systems and report which business-related performance measures were used in such real-world deployments. We summarize common challenges of measuring the business value in practice and critically discuss the value of algorithmic improvements and offline experiments as commonly done in academic environments. Overall, our review indicates that various open questions remain both regarding the realistic quantification of the business effects of recommenders and the performance assessment of recommendation algorithms in academia.

"Skills and Expertise" is a data-driven feature on LinkedIn, the world's largest professional online social network, which allows members to tag themselves with topics representing their areas of expertise. In this work, we present our experiences developing this large-scale topic extraction pipeline, which includes constructing a folksonomy of skills and expertise and implementing an inference and recommender system for skills. We also discuss a consequent set of applications, such as Endorsements, which allows members to tag themselves with topics representing their areas of expertise and for their connections to provide social proof, via an "endorse" action, of that member's competence in that topic.

LinkedIn skills: large-scale topic extraction and inference

Multidimensional data generated by members on websites has seen massive growth in recent years. OLAP is a well-suited solution for mining and analyzing this data. Providing insights derived from this analysis has become crucial for these websites to give members greater value. For example, LinkedIn, the largest professional social network, provides its professional members rich analytics features like "Who's Viewed My Profile?" and "Who's Viewed This Job?" The data behind these features form cubes that must be efficiently served at scale, and can be neatly sharded to do so. To serve our growing 160 million member base, we built a scalable and fast OLAP serving system called Avatara to solve this many, small cubes problem. At LinkedIn, Avatara has been powering several analytics features on the site for the past two years.

/pdf/avatara-olap-for-web-scale-analytics-products-3mjtd9v963.pdf

Avatara: OLAP for web-scale analytics products

This disclosure relates to systems and methods that include an electronic database related to members in a social network, the members including new members who have been members of the social network less than a predetermined time and established members who have been members of the social network greater than the predetermined time. A processor, coupled to the electronic database and the network interface, is configured to obtain an optimization criterion based on at least two constraints related to interaction of members in the social network, determine proposed interaction values based on the data, each proposed interaction value corresponding to pairs of members, the proposed interaction values including a new member proposed interaction value between at least one established member and at least one new member, modify the new member proposed interaction value based on an adjustment factor, and provide proposed interactions based the interaction values.

Multi-objective optimization for new members of a social network

In training of modern large natural language processing (NLP) models, it has become a common practice to split models using 3D parallelism to multiple GPUs. Such technique, however, suffers from a high overhead of inter-node communication. Compressing the communication is one way to mitigate the overhead by reducing the inter-node traffic volume; however, the existing compression techniques have critical limitations to be applied for NLP models with 3D parallelism in that 1) only the data parallelism traffic is targeted, and 2) the existing compression schemes already harm the model quality too much. In this paper, we present Optimus-CC, a fast and scalable distributed training framework for large NLP models with aggressive communication compression. Optimus-CC differs from existing communication compression frameworks in the following ways: First, we compress pipeline parallel (inter-stage) traffic. In specific, we compress the inter-stage backpropagation and the embedding synchronization in addition to the existing data-parallel traffic compression methods. Second, we propose techniques to avoid the model quality drop that comes from the compression. We further provide mathematical and empirical analyses to show that our techniques can successfully suppress the compression error. Lastly, we analyze the pipeline and opt to selectively compress those traffic lying on the critical path. This further helps reduce the compression error. We demonstrate our solution on a GPU cluster, and achieve superior speedup from the baseline state-of-the-art solutions for distributed training without sacrificing the model quality.

/pdf/optimus-cc-efficient-large-nlp-model-training-with-3d-13dilmxy.pdf

Optimus-CC: Efficient Large NLP Model Training with 3D Parallelism Aware Communication Compression

The invention relates to multi-target optimization for social network new members, and relates to a system and method of an electronic database relating to the social network new members; the members comprise new members with a time period, of becoming the social network new member, less than a preset time, and set members with a time period, of becoming the social network new member, more than a preset time A processor is coupled to the electronic database and an internet interface; the processor can obtain an optimize principle according to at least two restrains related to the social network members; the processor can determine a proposed interaction value according to data, each proposed interaction value responds to one member, and at least comprises a set member and a new member; the processor can correct the new member proposed interaction value according to factors, and can provide interaction according to the interaction value

Hyung Jin Kim

Papers

LinkedIn skills: large-scale topic extraction and inference

Avatara: OLAP for web-scale analytics products

Multi-objective optimization for new members of a social network

Optimus-CC: Efficient Large NLP Model Training with 3D Parallelism Aware Communication Compression

Multi-target optimization for social network new member