A modern approach to recommendation will look at this log in order to improve future recommendations. By examining how similar users respond to different recommendations it becomes possible to discover better recommendations and continue to improve the system. This procedure of learning by experimentation in some respects mimics randomized control trials in medicine where populations are split into two and different treatments are delivered to similar groups. Medical trials are however simpler, as an intervention or a placebo is administered to each group and then long-term impacts are observed with no further interventions delivered. The challenges of credit attribution in the case of delayed reward and multiple actions. In contrast with medical trials, where the treatment is frequently a binary variable, recommender systems will deliver multiple actions at variable times leading to combinatorially complex treatments. For simplicity, in our previous work on RecoGym[2], we assumed that both the current recommendation and the reward are conditionally independent on past actions, therefore making the recommendation amenable to contextual bandits and supervised value modeling approaches.

Given the convenience of collecting information through online services, recommender systems now consume large scale data and play a more important role in improving user experience. With the recent emergence of Graph Neural Networks (GNNs), GNN-based recommender models have shown the advantage of modeling the recommender system as a user-item bipartite graph to learn representations of users and items. However, such models are expensive to train and difficult to perform frequent updates to provide the most up-to-date recommendations. In this work, we propose to update GNN-based recommender models incrementally so that the computation time can be greatly reduced and models can be updated more frequently. We develop a Graph Structure Aware Incremental Learning framework, GraphSAIL, to address the commonly experienced catastrophic forgetting problem that occurs when training a model in an incremental fashion. Our approach preserves a user's long-term preference (or an item's long-term property) during incremental model updating. GraphSAIL implements a graph structure preservation strategy which explicitly preserves each node's local structure, global structure, and self-information, respectively. We argue that our incremental training framework is the first attempt tailored for GNN based recommender systems and demonstrate its improvement compared to other incremental learning techniques on two public datasets. We further verify the effectiveness of our framework on a large-scale industrial dataset.

Using personalized explanations to support recommendations has been shown to increase trust and perceived quality. However, to actually obtain better recommendations, there needs to be a means for users to modify the recommendation criteria by interacting with the explanation. We present a novel technique using aspect markers that learns to generate personalized explanations of recommendations from review texts, and we show that human users significantly prefer these explanations over those produced by state-of-the-art techniques. Our work's most important innovation is that it allows users to react to a recommendation by critiquing the textual explanation: removing (symmetrically adding) certain aspects they dislike or that are no longer relevant (symmetrically that are of interest). The system updates its user model and the resulting recommendations according to the critique. This is based on a novel unsupervised critiquing method for single- and multi-step critiquing with textual explanations. Experiments on two real-world datasets show that our system is the first to achieve good performance in adapting to the preferences expressed in multi-step critiquing.

The robot possesses an infrared thermal imager and a visual light camera, thereby giving them the ability to replace 24-hour manual inspection. Artificial intelligence is about to trigger explosive changes in our lives, work, and leisure, but few understand what the technology can do beyond Amazon AMZN's Alexa or Apple AAPL's Siri. These are examples of virtual assistant or'weak AI' technology -- the most common example of AI application. But in the data-driven energy sector, sophisticated machine learning is paving the way for'strong AI' to improve efficiency, forecasting, trading, and user accessibility. Electricity is a commodity that can be bought, sold, and traded in open markets.

Nope, the new Lenovo Smart Clock Essential doesn't do videos, slideshows or fancy user interfaces. Instead, you get a back-to-basics LED, although Google Assistant is still under the hood. Slated to go on sale this fall for $50, the Smart Clock Essential is--essentially?--Lenovo's take on Amazon's Alexa-powered Echo Dot with Clock, although the Smart Clock Essential's four-inch LED display is slightly more detailed than the Echo Dot's spare digital readout, featuring the temperature and weather as well as the time. As with last year's Lenovo Smart Clock (which we've reviewed), the Smart Clock Essential has a fabric-covered base and a single 1.5-inch 3W speaker, while a two-microphone array lets you chat with Google Assistant. Naturally, you can ask the Assistant to set alarms, check the day's agenda, play tunes, and control your smart home devices.

What you consume on social media through Facebook, Twitter, Instagram, the personalization you experience when you search, listen, and watch through Google, Spotify, Youtube, what you discover using Airbnb and UberEats, all of these products are powered by machine learning recommender systems. There is also a hybrid based recommender system, which mixes collaborative and content-based filtering. These machine learning and AI algorithms are what power the consumer products we use every day. Recommendation algorithms make optimizations based on the key assumption that only similarities are good. If you like fantasy books, you will get recommended more fantasy books, if you like progressive politics, you will get recommended more progressive politics.

It's been more than a year since Lenovo launched the Google-powered Smart Clock, and that little thing has been pretty well-received. The company noted in a press briefing that the device has received a 4.4-star rating around the world and that 80 percent of its users said they use it in their bedrooms. Director of global product marketing Wahid Razali said the Smart Clock is "simpler than a smart display and more useful than a small smart speaker." It's hard to imagine the clock getting any more basic than that, but Lenovo's latest offering proves it can be done (for better or worse). The company today unveiled the Smart Clock Essential, which is basically a Google smart speaker with an LED screen to show the time.

As Apple's artificial language and machine learning initiatives continue to expand, its interest in attracting talent has grown -- a theme that's barely under the surface of the company's occasionally updated Machine Learning Research blog. Now Apple is openly seeking to recruit U.S. and European candidates with niche expertise for a yearlong AI/ML residency program, promising immersion and mentoring that will advance their careers. The goal is apparently to find people whose interests aren't necessarily AI/ML specific, then give them the knowledge and tools to apply machine learning and deep learning to their disciplines -- a process that will widen Apple's ability to solve users' problems in those disciplines. Apple says its ideal candidates would come from fields such as cognitive science, psychology, physics, robotics, public health, or computer graphics, but in any case should have programming proficiency and either a graduate degree or equivalent industry experience. Residencies are currently being offered in Cupertino, California; Seattle, Washington; Cambridge, U.K.; Zurich, and "various locations within Germany" for a summer 2021 start date, with assignment descriptions that vary between locations.

You trained a machine learning model, validated its performance across several metrics which are looking good, you put it in production, and then something unforeseen happened (a pandemic like COVID-19 arrived) and the model predictions have gone crazy. You fell victim to a phenomenon called concept drift. But don't feel bad as it happens to all of us all the time. Heraclitus, the Greek philosopher said, "Change is the only constant in life." In the dynamic world, nothing is constant.

We know that the range of AI-loaded smart products is constantly expanding. But what's less obvious is how AI is also transforming the world of services – enabling service-based businesses to improve their offering, and even develop entirely new services and revenue streams that are underpinned by AI. Just as in product-based businesses, AI has become a driving factor for success in the service sector. Here are three ways businesses are delivering a better service through AI. AI provides incredible opportunities to get to know your customers – what they like and don't like, what they actually do (as opposed to what they say they do), how they engage with your service, what factors would encourage them to engage more deeply, and do on.