Providing meaningful recommendations in a content marketplace is challenging due to the fact that users are not the final content consumers. Instead, most users are creatives whose interests, linked to the projects they work on, change rapidly and abruptly. To address the challenging task of recommending images to content creators, we design a RecSys that learns visual styles preferences transversal to the semantics of the projects users work on. We analyze the challenges of the task compared to content-based recommendations driven by semantics, propose an evaluation setup, and explain its applications in a global image marketplace. This technical report is an extension of the paper "Learning Users' Preferred Visual Styles in an Image Marketplace", presented at ACM RecSys '22.

Causal graph, as an effective and powerful tool for causal modeling, is usually assumed as a Directed Acyclic Graph (DAG). However, recommender systems usually involve feedback loops, defined as the cyclic process of recommending items, incorporating user feedback in model updates, and repeating the procedure. As a result, it is important to incorporate loops into the causal graphs to accurately model the dynamic and iterative data generation process for recommender systems. However, feedback loops are not always beneficial since over time they may encourage more and more narrowed content exposure, which if left unattended, may results in echo chambers. As a result, it is important to understand when the recommendations will lead to echo chambers and how to mitigate echo chambers without hurting the recommendation performance. In this paper, we design a causal graph with loops to describe the dynamic process of recommendation. We then take Markov process to analyze the mathematical properties of echo chamber such as the conditions that lead to echo chambers. Inspired by the theoretical analysis, we propose a Dynamic Causal Collaborative Filtering ($\partial$CCF) model, which estimates users' post-intervention preference on items based on back-door adjustment and mitigates echo chamber with counterfactual reasoning. Multiple experiments are conducted on real-world datasets and results show that our framework can mitigate echo chambers better than other state-of-the-art frameworks while achieving comparable recommendation performance with the base recommendation models.

A bill is headed to the governor's desk that would create a path for suing people who send unsolicited sexual pictures, but the legislation stops short of making "cyberflashing" a crime in California. If signed by Gov. Gavin Newsom, SB 53 by Sen. Connie Leyva (D-Chino) will allow Californians to take someone to civil court over unwanted lewd photos sent to them electronically; plaintiffs who win a suit could get up to $30,000 in damages. The legislation, approved Monday on the Senate floor in a 37-0 vote, comes after reports of men using the AirDrop iPhone feature to send lewd pictures to nearby strangers or on online dating apps without consent from the recipients. The bill applies to senders over 18 and defines obscene images as anything that depicts a person engaging in sexual acts, including masturbation, or photos of genitals "in a patently offensive way, and that, taken as a whole, lacks serious literary, artistic, political, or scientific value." The bill is sponsored by the women-centered dating app Bumble.

In the digital world, the two buzzwords discussed everywhere include Artificial Intelligence and Machine Learning. These technologies have revolutionized the ways businesses function and also the ways we execute our routine tasks. These have gradually seeped into the business world as well as our personal lives. It is through Artificial Intelligence and Machine Learning that every company is on the way to becoming a tech company. The profound implications of Artificial Intelligence in both business and society have made this technology the next digital frontier.

An industrial recommender system generally presents a hybrid list that contains results from multiple subsystems. In practice, each subsystem is optimized with its own feedback data to avoid the disturbance among different subsystems. However, we argue that such data usage may lead to sub-optimal online performance because of the \textit{data sparsity}. To alleviate this issue, we propose to extract knowledge from the \textit{super-domain} that contains web-scale and long-time impression data, and further assist the online recommendation task (downstream task). To this end, we propose a novel industrial \textbf{K}nowl\textbf{E}dge \textbf{E}xtraction and \textbf{P}lugging (\textbf{KEEP}) framework, which is a two-stage framework that consists of 1) a supervised pre-training knowledge extraction module on super-domain, and 2) a plug-in network that incorporates the extracted knowledge into the downstream model. This makes it friendly for incremental training of online recommendation. Moreover, we design an efficient empirical approach for KEEP and introduce our hands-on experience during the implementation of KEEP in a large-scale industrial system. Experiments conducted on two real-world datasets demonstrate that KEEP can achieve promising results. It is notable that KEEP has also been deployed on the display advertising system in Alibaba, bringing a lift of $+5.4\%$ CTR and $+4.7\%$ RPM.

Every weekday, The Detail makes sense of the big news stories. This week, we talked about the burgeoning concerns over artificial intelligence, talked to two former political party presidents about their hidden role, visited a food bank operating in the wealthy North Shore, looked at the fight to keep foot-and-mouth disease out of our farms, and finished the week with a new Supreme Court case trying to hold big corporations liable for contributing to climate change. Whakarongo mai to any episodes you might have missed. Artificial intelligence systems running rogue might seem like the stuff of science-fiction, but these systems are increasingly common in many high-tech elements of society, from self-driving cars to digital assistants, facial identification, Netflix recommendations, and much, much more. The capabilities of artificial intelligence are growing at pace; a pace that's outstripping regulatory frameworks.

Building a Recommendation System is not a trivial task and it comes with its own set of problems and challenges. This article is an effort to provide readers a deeper insight into building recommendation systems. A Recommendation system is an application of machine learning that provides recommendations to users on what they might like based on their historical preferences. It can be further defined as a system that produces individualized recommendations as output or has the effect of guiding the user in a personalized way to interesting objects in a larger space of possible options. Collaborative methods for Recommendation systems are methods that are based solely on the past interactions recorded between users and items in order to produce new recommendations. These interactions are stored in the so-called "user-item interactions matrix".

Originally published on Towards AI the World's Leading AI and Technology News and Media Company. If you are building an AI-related product or service, we invite you to consider becoming an AI sponsor. At Towards AI, we help scale AI and technology startups. Let us help you unleash your technology to the masses. Whenever we visit a shopping mall to buy a new pair of shoes or clothes, we find a dedicated person who helps us with the kind of products we should buy based on our preferences and makes our job simpler.

We've been long working on improving the user experience in UGC products with machine learning. Here are our ten key lessons of implementing recommendation systems in business to build a really good product. The global task of the recommendation system is to select a shortlist of content from a large catalog that is most suitable for a particular user. The content itself can be different -- from products in the online store and articles to banking services. FunCorp product team works with the most interesting kind of content -- we recommend memes.

With the recent advances of conversational recommendations, the recommender system is able to actively and dynamically elicit user preference via conversational interactions. To achieve this, the system periodically queries users' preference on attributes and collects their feedback. However, most existing conversational recommender systems only enable the user to provide absolute feedback to the attributes. In practice, the absolute feedback is usually limited, as the users tend to provide biased feedback when expressing the preference. Instead, the user is often more inclined to express comparative preferences, since user preferences are inherently relative. To enable users to provide comparative preferences during conversational interactions, we propose a novel comparison-based conversational recommender system. The relative feedback, though more practical, is not easy to be incorporated since its feedback scale is always mismatched with users' absolute preferences. With effectively collecting and understanding the relative feedback from an interactive manner, we further propose a new bandit algorithm, which we call RelativeConUCB. The experiments on both synthetic and real-world datasets validate the advantage of our proposed method, compared to the existing bandit algorithms in the conversational recommender systems.