There is a soaring interest in the news recommendation research scenario due to the information overload. To accurately capture users' interests, we propose to model multi-modal features, in addition to the news titles that are widely used in existing works, for news recommendation. Besides, existing research pays little attention to the click decision-making process in designing multi-modal modeling modules. In this work, inspired by the fact that users make their click decisions mostly based on the visual impression they perceive when browsing news, we propose to capture such visual impression information with visual-semantic modeling for news recommendation. Specifically, we devise the local impression modeling module to simultaneously attend to decomposed details in the impression when understanding the semantic meaning of news title, which could explicitly get close to the process of users reading news. In addition, we inspect the impression from a global view and take structural information, such as the arrangement of different fields and spatial position of different words on the impression, into the modeling of multiple modalities. To accommodate the research of visual impression-aware news recommendation, we extend the text-dominated news recommendation dataset MIND by adding snapshot impression images and will release it to nourish the research field. Extensive comparisons with the state-of-the-art news recommenders along with the in-depth analyses demonstrate the effectiveness of the proposed method and the promising capability of modeling visual impressions for the content-based recommenders.

Collaborative filtering (CF) is a widely studied research topic in recommender systems. The learning of a CF model generally depends on three major components, namely interaction encoder, loss function, and negative sampling. While many existing studies focus on the design of more powerful interaction encoders, the impacts of loss functions and negative sampling ratios have not yet been well explored. In this work, we show that the choice of loss function as well as negative sampling ratio is equivalently important. More specifically, we propose the cosine contrastive loss (CCL) and further incorporate it to a simple unified CF model, dubbed SimpleX. Extensive experiments have been conducted on 11 benchmark datasets and compared with 29 existing CF models in total. Surprisingly, the results show that, under our CCL loss and a large negative sampling ratio, SimpleX can surpass most sophisticated state-of-the-art models by a large margin (e.g., max 48.5% improvement in NDCG@20 over LightGCN). We believe that SimpleX could not only serve as a simple strong baseline to foster future research on CF, but also shed light on the potential research direction towards improving loss function and negative sampling.

We investigate the design of recommendation systems that can efficiently learn from sparse and delayed feedback. Deep Exploration can play an important role in such contexts, enabling a recommendation system to much more quickly assess a user's needs and personalize service. We design an algorithm based on Thompson Sampling that carries out Deep Exploration. We demonstrate through simulations that the algorithm can substantially amplify the rate of positive feedback relative to common recommendation system designs in a scalable fashion. These results demonstrate promise that we hope will inspire engineering of production recommendation systems that leverage Deep Exploration.

With the hardware development of mobile devices, it is possible to build the recommendation models on the mobile side to utilize the fine-grained features and the real-time feedbacks. Compared to the straightforward mobile-based modeling appended to the cloud-based modeling, we propose a Slow-Fast learning mechanism to make the Mobile-Cloud Collaborative recommendation (MC$^2$-SF) mutual benefit. Specially, in our MC$^2$-SF, the cloud-based model and the mobile-based model are respectively treated as the slow component and the fast component, according to their interaction frequency in real-world scenarios. During training and serving, they will communicate the prior/privileged knowledge to each other to help better capture the user interests about the candidates, resembling the role of System I and System II in the human cognition. We conduct the extensive experiments on three benchmark datasets and demonstrate the proposed MC$^2$-SF outperforms several state-of-the-art methods.

Though recent end-to-end neural models have shown promising progress on Conversational Recommender System (CRS), two key challenges still remain. First, the recommended items cannot be always incorporated into the generated replies precisely and appropriately. Second, only the items mentioned in the training corpus have a chance to be recommended in the conversation. To tackle these challenges, we introduce a novel framework called NTRD for recommender dialogue system that decouples the dialogue generation from the item recommendation. NTRD has two key components, i.e., response template generator and item selector. The former adopts an encoder-decoder model to generate a response template with slot locations tied to target items, while the latter fills in slot locations with the proper items using a sufficient attention mechanism. Our approach combines the strengths of both classical slot filling approaches (that are generally controllable) and modern neural NLG approaches (that are generally more natural and accurate). Extensive experiments on the benchmark ReDial show our NTRD significantly outperforms the previous state-of-the-art methods. Besides, our approach has the unique advantage to produce novel items that do not appear in the training set of dialogue corpus. The code is available at \url{https://github.com/jokieleung/NTRD}.

The smart connected home is the next step in our houses' growth and how we interact with them. The various systems in our houses are developing as technology improves, much as lighting has progressed from candles to gas to electricity. The smart home is rapidly expanding. While all of these new smart home technologies may appear intimidating and difficult at first, the introduction of artificially intelligent assistants and voice control has made it much easier to accept. Here is a list of the essential smart home devices which work on smart home technologies.

Sequential Recommendation aims to recommend items that a target user will interact with in the near future based on the historically interacted items. While modeling temporal dynamics is crucial for sequential recommendation, most of the existing studies concentrate solely on the user side while overlooking the sequential patterns existing in the counterpart, i.e., the item side. Although a few studies investigate the dynamics involved in the dual sides, the complex user-item interactions are not fully exploited from a global perspective to derive dynamic user and item representations. In this paper, we devise a novel Dynamic Representation Learning model for Sequential Recommendation (DRL-SRe). To better model the user-item interactions for characterizing the dynamics from both sides, the proposed model builds a global user-item interaction graph for each time slice and exploits time-sliced graph neural networks to learn user and item representations. Moreover, to enable the model to capture fine-grained temporal information, we propose an auxiliary temporal prediction task over consecutive time slices based on temporal point process. Comprehensive experiments on three public real-world datasets demonstrate DRL-SRe outperforms the state-of-the-art sequential recommendation models with a large margin.

Google is updating critical features for the millions of drivers who depend on its technology to help them get around. The tech giant announced the upcoming changes Thursday to Google Assistant and Android Auto driving modes and a new automaker, Honda, will have Google technology installed in its vehicles. Google said that drivers using Google Assistant on Android phones will soon see a new dashboard they say will reduce "the need to fiddle with your phone while also making sure you stay focused on the road." Instead of scrolling while driving, Google said drivers could tap to see who just called or sent a text and have access to several apps to listen to music with the new dashboard. The dashboard will also include a new messaging update where drivers can say, "Hey Google, turn on auto-read," to hear their new messages read aloud when they come in and respond by voice.

According to a survey conducted by PwC, 72% of business leaders use AI for their business advantage. The Digital marketing world has been restructured immensely since the emergence of AI. It helps companies develop powerful digital strategies, optimizes campaigns, and improves return on investment. Teleflora, a floral company in the US, used AI marketing to build new customers' profiles and improve customer loyalty. Using these historical data, Teleflora used AI marketing to predict the future customer behavior of different audience segments.

This is the first post in an intended series on what is the current state of Artificial Intelligence capabilities, and what we can expect in the relative short term. I will be at odds with the more outlandish claims that are circulating in the press, and amongst what I consider an alarmist group that includes people in the AI field and outside of it. In this post I start to introduce some of the key components of my future arguments, as well as show how different any AI system might be from us humans. Some may recognize the title of this post as an homage to the 1974 paper by Thomas Nagel, "What Is It Like to Be a Bat?". Two more recent books, one from 2009 by Alexandra Horowitz on dogs, and one from 2016 by Peter Godfrey-Smith on octopuses also pay homage to Nagel's paper each with a section of a chapter titled "What it is like", and "What It's Like", respectively, giving affirmative responses to their own questions about what is it like to be a dog, or an octopus.