Recently, a former Google researcher claimed that some algorithms used by the company reached sentient capabilities well above their initial design. Phillipa Louvois rules that Data, the Enterprise's android, is not the property of Starfleet, arguing: "We have all been dancing around the basic issue: does Data have a soul? I don't know that he has. I don't know that I have. But I have got to give him the freedom to explore that question himself."

Next Point-of-Interest (POI) recommendation has become an indispensable functionality in Location-based Social Networks (LBSNs) due to its effectiveness in helping people decide the next POI to visit. However, accurate recommendation requires a vast amount of historical check-in data, thus threatening user privacy as the location-sensitive data needs to be handled by cloud servers. Although there have been several on-device frameworks for privacy-preserving POI recommendations, they are still resource-intensive when it comes to storage and computation, and show limited robustness to the high sparsity of user-POI interactions. On this basis, we propose a novel decentralized collaborative learning framework for POI recommendation (DCLR), which allows users to train their personalized models locally in a collaborative manner. DCLR significantly reduces the local models' dependence on the cloud for training, and can be used to expand arbitrary centralized recommendation models. To counteract the sparsity of on-device user data when learning each local model, we design two self-supervision signals to pretrain the POI representations on the server with geographical and categorical correlations of POIs. To facilitate collaborative learning, we innovatively propose to incorporate knowledge from either geographically or semantically similar users into each local model with attentive aggregation and mutual information maximization. The collaborative learning process makes use of communications between devices while requiring only minor engagement from the central server for identifying user groups, and is compatible with common privacy preservation mechanisms like differential privacy. We evaluate DCLR with two real-world datasets, where the results show that DCLR outperforms state-of-the-art on-device frameworks and yields competitive results compared with centralized counterparts.

Modeling the evolution of user preference is essential in recommender systems. Recently, dynamic graph-based methods have been studied and achieved SOTA for recommendation, majority of which focus on user's stable long-term preference. However, in real-world scenario, user's short-term preference evolves over time dynamically. Although there exists sequential methods that attempt to capture it, how to model the evolution of short-term preference with dynamic graph-based methods has not been well-addressed yet. In particular: 1) existing methods do not explicitly encode and capture the evolution of short-term preference as sequential methods do; 2) simply using last few interactions is not enough for modeling the changing trend. In this paper, we propose Long Short-Term Preference Modeling for Continuous-Time Sequential Recommendation (LSTSR) to capture the evolution of short-term preference under dynamic graph. Specifically, we explicitly encode short-term preference and optimize it via memory mechanism, which has three key operations: Message, Aggregate and Update. Our memory mechanism can not only store one-hop information, but also trigger with new interactions online. Extensive experiments conducted on five public datasets show that LSTSR consistently outperforms many state-of-the-art recommendation methods across various lines.

What makes deep learning-based recommendation systems different from the traditional recommender systems is their ability to analyze complex interaction patterns between the visitor and the products and construct additional features automatically, leading to recommendations that precisely match the visitors' intent and affinity. Deep learning-based systems overcome the weaknesses of the two more traditional types of recommender systems: content-based and collaborative filtering. See how CartUp AI makes deep learning and other cutting-edge AI technologies available to merchants.

We saw a number of gadgets go on sale this week as July comes to a close. Both Amazon's Echo smart speaker and the Echo Show 5 have been discounted, with the Echo now down to the same price as it was on Prime Day earlier this month. The Apple TV 4K is nearly $50 off and down to $130, and you can save $300 on the 16-inch MacBook Pro as well. DJI's Action 2 combo pack remains on sale for $279, and if you're on the market for a new smartphone, Amazon will give you a free $50 gift card when you buy the new Google Pixel 6a. Here are the best tech deals from this week that you can still get today.

If you're finally returning to the office after months of working from home during the pandemic, you may find there are a few adjustments to make - from getting dressed below the waist to waking up more than three minutes before your first call. But luckily, keeping up with your romantic connections shouldn't be an issue, after Tinder announced it is revamping its'Desk Mode' feature, so users can continue to swipe while at their desks. Tinder users can access Desk Mode by logging into Tinder's desktop site on a computer, where they will see a briefcase icon in the upper right-hand corner of the screen. In that awkward moment when a pesky boss or chatty coworker appears over your shoulder mid-flirt, you can click the icon to bring up a mock report, creating the illusion you were doing work all along. Tinder users can access Desk Mode by logging into Tinder's desktop site on a computer, where they will see a briefcase icon in the upper right-hand corner of the screen.

The production, shipping, usage, and disposal of consumer goods have a substantial impact on greenhouse gas emissions and the depletion of resources. Modern retail platforms rely heavily on Machine Learning (ML) for their search and recommender systems. Thus, ML can potentially support efforts towards more sustainable consumption patterns, for example, by accounting for sustainability aspects in product search or recommendations. However, leveraging ML potential for reaching sustainability goals requires data on sustainability. Unfortunately, no open and publicly available database integrates sustainability information on a product-by-product basis. In this work, we present the GreenDB, which fills this gap. Based on search logs of millions of users, we prioritize which products users care about most. The GreenDB schema extends the well-known schema.org Product definition and can be readily integrated into existing product catalogs to improve sustainability information available for search and recommendation experiences. We present our proof of concept implementation of a scraping system that creates the GreenDB dataset.

Artificial intelligence, like the Internet of Things, has the potential to alter the economy with technological advancements drastically. FREMONT, CA: Artificial intelligence is seen as a supplement to, rather than a replacement for, human intelligence and resourcefulness. It is a type of software that can make judgments on its own and respond in situations that the creators did not anticipate. The artificial intelligence software can then present the human user with synthesized routes of action. As a result, businesses can employ AI to help the game out the potential outcomes of each action and streamline the decision-making process.

This paper studies user attributes in light of current concerns in the recommender system community: diversity, coverage, calibration, and data minimization. In experiments with a conventional context-aware recommender system that leverages side information, we show that user attributes do not always improve recommendation. Then, we demonstrate that user attributes can negatively impact diversity and coverage. Finally, we investigate the amount of information about users that ``survives'' from the training data into the recommendation lists produced by the recommender. This information is a weak signal that could in the future be exploited for calibration or studied further as a privacy leak.

Recommendation systems when employed in markets play a dual role: they assist users in selecting their most desired items from a large pool and they help in allocating a limited number of items to the users who desire them the most. Despite the prevalence of capacity constraints on allocations in many real-world recommendation settings, a principled way of incorporating them in the design of these systems has been lacking. Motivated by this, we propose an interactive framework where the system provider can enhance the quality of recommendations to the users by opportunistically exploring allocations that maximize user rewards and respect the capacity constraints using appropriate pricing mechanisms. We model the problem as an instance of a low-rank combinatorial multi-armed bandit problem with selection constraints on the arms. We employ an integrated approach using techniques from collaborative filtering, combinatorial bandits, and optimal resource allocation to provide an algorithm that provably achieves sub-linear regret, namely $\tilde{\mathcal{O}} ( \sqrt{N M (N+M) RT} )$ in $T$ rounds for a problem with $N$ users, $M$ items and rank $R$ mean reward matrix. Empirical studies on synthetic and real-world data also demonstrate the effectiveness and performance of our approach.