In this work, we present a new dataset for conversational recommendation over knowledge graphs in e-commerce platforms called COOKIE. The dataset is constructed from an Amazon review corpus by integrating both user-agent dialogue and custom knowledge graphs for recommendation. Specifically, we first construct a unified knowledge graph and extract key entities between user--product pairs, which serve as the skeleton of a conversation. Then we simulate conversations mirroring the human coarse-to-fine process of choosing preferred items. The proposed baselines and experiments demonstrate that our dataset is able to provide innovative opportunities for conversational recommendation.

Most recommendation engines today are based on predicting user engagement, e.g. predicting whether a user will click on an item or not. However, there is potentially a large gap between engagement signals and a desired notion of "value" that is worth optimizing for. We use the framework of measurement theory to (a) confront the designer with a normative question about what the designer values, (b) provide a general latent variable model approach that can be used to operationalize the target construct and directly optimize for it, and (c) guide the designer in evaluating and revising their operationalization. We implement our approach on the Twitter platform on millions of users. In line with established approaches to assessing the validity of measurements, we perform a qualitative evaluation of how well our model captures a desired notion of "value".

In recent years, text-aware collaborative filtering methods have been proposed to address essential challenges in recommendations such as data sparsity, cold start problem, and long-tail distribution. However, many of these text-oriented methods rely heavily on the availability of text information for every user and item, which obviously does not hold in real-world scenarios. Furthermore, specially designed network structures for text processing are highly inefficient for on-line serving and are hard to integrate into current systems. In this paper, we propose a flexible neural recommendation framework, named Review Regularized Recommendation, short as R3. It consists of a neural collaborative filtering part that focuses on prediction output, and a text processing part that serves as a regularizer. This modular design incorporates text information as richer data sources in the training phase while being highly friendly for on-line serving as it needs no on-the-fly text processing in serving time. Our preliminary results show that by using a simple text processing approach, it could achieve better prediction performance than state-of-the-art text-aware methods.

Graph representation learning is gaining popularity in a wide range of applications, such as social networks analysis, computational biology, and recommender systems. However, different with positive results from many academic studies, applying graph neural networks (GNNs) in a real-world application is still challenging due to non-stationary environments. The underlying distribution of streaming data changes unexpectedly, resulting in different graph structures (a.k.a., concept drift). Therefore, it is essential to devise a robust graph learning technique so that the model does not overfit to the training graphs. In this work, we present Hop Sampling, a straightforward regularization method that can effectively prevent GNNs from overfishing. The hop sampling randomly selects the number of propagation steps rather than fixing it, and by doing so, it encourages the model to learn meaningful node representation for all intermediate propagation layers and to experience a variety of plausible graphs that are not in the training set. Particularly, we describe the use case of our method in recommender systems, a representative example of the real-world non-stationary case. We evaluated hop sampling on a large-scale real-world LINE dataset and conducted an online A/B/n test in LINE Coupon recommender systems of LINE Wallet Tab. Experimental results demonstrate that the proposed scheme improves the prediction accuracy of GNNs. We observed hop sampling provides 7.97% and 16.93% improvements for NDCG and MAP compared to non-regularized GNN models in our online service. Furthermore, models using hop sampling alleviate the oversmoothing issue in GNNs enabling a deeper model as well as more diversified representation.

SilverTech, a national digital marketing and technology agency, announced an official partnership with the technology provider, Akumina, of Nashua, New Hampshire. The Akumina platform is a modern Intranet & Employee Experience Platform (EXP). SilverTech will be utilizing the Akumina platform to deliver transformative workspace solutions and will offer clients a branded, hyper-personalized workplace experience that addresses the needs of Communications, IT, Human Resources, Content Managers, and Administrators. SilverTech digital strategists, user experience designers, and web developers will brand, customize, and implement Akumina's EXP platform and integrate it with client systems and data. "We've been helping our clients deliver exceptional customer experiences for over 20 years. We're really excited to partner with Akumina to help our clients now deliver exceptional experiences to their employees as well," said Derek Barka, CTO of SilverTech.

Zoom, the video conferencing app of the COVID era, is about to land on Amazon, Facebook, and Google smart displays. In a press release, Zoom announced it will make its initial debut on Facebook Portal displays next month, while Zoom integrations for Amazon Echo Show devices and Google Assistant-enabled displays, including the Nest Hub Max, are due this fall. The arrival of Zoom on the Amazon Echo Show (starting with the Echo Show 8) will be a major boost for Amazon's smart display, which up until now was only capable of one-on-one video calling. Google announced group calling on its Google smart displays via Google Meet and Duo in late June. Facebook's Portal smart displays support group calls of up to 50 people with Messenger Rooms and Workplace Rooms.

While making predictions may be easy, delivering accurate ones is an altogether different story. That's why in this column we won't just be looking at the most important trends of 2020, but we'll also look at how the ideas we highlighted last year have developed. In summarizing the trends of 2020, one conclusion we've come to is that society is getting increasingly interested in AI technology, in terms of both the threats it poses and common knowledge about other problems that need to be addressed. In our AI Trends 2019 blogpost we chronicled last year's most important trends and directions of development to watch. It was shortly after launching the AI Monthly Digest, a monthly summary of the most significant and exciting machine learning news.

Zoom has just announced that its "Zoom for Home" video conferencing platform is coming to Amazon's Echo Show line, Google's smart displays plus Facebook's Portal devices. Zoom will arrive on Portal in September, while it's slated to be available on the Echo Show (beginning with the Echo Show 8) and Google-powered displays before the end of the year. The company only launched its Zoom for Home initiative a month ago, when it announced a partnership with third-party manufacturers to create a line of "Zoom for Home" hardware. The first Zoom for Home product was the DTEN ME, and was designed for business professionals. By expanding to existing devices like the Echo Show, Google-powered displays (that includes the Nest Hub Max as well as other Assistant-powered displays like the Lenovo Smart Display) and the Portal however, Zoom is widening its footprint into the consumer space as well.

After frustrating stay-at-home workers and parents looking for an easy way to connect their kids to Zoom because it wasn't available, the world's most popular video meeting application is finally coming to Amazon, Google and Facebook video display units. The Echo Show, Google Nest Hub Max and Facebook Portal were originally released as a way for folks to engage in video chatting and home entertainment without the bother of turning on the computer, phone or TV. That there would be a coronavirus that sent Zoom usage up 10x in less than a year wasn't foreseen, nor the need to have a dedicated video display that could handle one-touch setup for the meetings and classes, without the bother of phones and computers. Fun:How to make video meetings more like in-person experience? But now, Zoom is finally coming to the devices, first to Portal, in September, the latest version of the Amazon Echo Show (version 8) and Google's Nest Hub Max, but not until later this year.

Typical SVD is less effective when data is not enough. How to leverage attention model to solve the cold start problem? Although SVD provides a satisfactory solution to recommendation system, it is less effective when the new items did not accumulate enough data. In this article, I will show you how to leverage the attention mechanism to solve the cold start problem in recommendation system. Attention Mechanism has a long history of applications and recently introduced to solve problems in NLP.