User behavior and feature interactions are crucial in deep learning-based recommender systems. There has been a diverse set of behavior modeling and interaction exploration methods in the literature. Nevertheless, the design of task-aware recommender systems still requires feature engineering and architecture engineering from domain experts. In this work, we introduce AMER, namely Automatic behavior Modeling and interaction Exploration in Recommender systems with Neural Architecture Search (NAS). The core contributions of AMER include the three-stage search space and the tailored three-step searching pipeline. In the first step, AMER searches for residual blocks that incorporate commonly used operations in the block-wise search space of stage 1 to model sequential patterns in user behavior. In the second step, it progressively investigates useful low-order and high-order feature interactions in the non-sequential interaction space of stage 2. Finally, an aggregation multi-layer perceptron (MLP) with shortcut connection is selected from flexible dimension settings of stage~3 to combine features extracted from the previous steps. For efficient and effective NAS, AMER employs the one-shot random search in all three steps. Further analysis reveals that AMER's search space could cover most of the representative behavior extraction and interaction investigation methods, which demonstrates the universality of our design. The extensive experimental results over various scenarios reveal that AMER could outperform competitive baselines with elaborate feature engineering and architecture engineering, indicating both effectiveness and robustness of the proposed method.

Apple's Siri and Google's voice assistant have both been updated to respond to questions about Black Lives Matter, and rebuff the sentiment behind the response "All Lives Matter." As spotted by sports blogger David Gardner, when asked "Do black lives matter?", Google's Assistant will respond: "Black Lives Matter. Black people deserve the same freedoms afforded to everyone in this country, and recognising the injustice they face is the first step towards fixing it." When asked "Do all lives matter", the Assistant will respond: "Saying'Black Lives Matter' doesn't mean that all lives don't. It means Black lives are at risk in ways others are not."

The lack of bias management in Recommender Systems leads to minority groups receiving unfair recommendations. Moreover, the trade-off between equity and precision makes it difficult to obtain recommendations that meet both criteria. Here we propose a Deep Learning based Collaborative Filtering algorithm that provides recommendations with an optimum balance between fairness and accuracy without knowing demographic information about the users. Experimental results show that it is possible to make fair recommendations without losing a significant proportion of accuracy.

Speech-based virtual assistants, such as Amazon Alexa, Google assistant, and Apple Siri, typically convert users' audio signals to text data through automatic speech recognition (ASR) and feed the text to downstream dialog models for natural language understanding and response generation. The ASR output is error-prone; however, the downstream dialog models are often trained on error-free text data, making them sensitive to ASR errors during inference time. To bridge the gap and make dialog models more robust to ASR errors, we leverage an ASR error simulator to inject noise into the error-free text data, and subsequently train the dialog models with the augmented data. Compared to other approaches for handling ASR errors, such as using ASR lattice or end-to-end methods, our data augmentation approach does not require any modification to the ASR or downstream dialog models; our approach also does not introduce any additional latency during inference time. We perform extensive experiments on benchmark data and show that our approach improves the performance of downstream dialog models in the presence of ASR errors, and it is particularly effective in the low-resource situations where there are constraints on model size or the training data is scarce.

Ever wished you could poll the entire household about what they want for dinner, even when everyone's in a different room? Thanks to a newly updated Alexa feature, you can do just that. Alexa's aptly named "Drop in" feature, which lets you connect to a nearby Echo speaker or display and have a two-way conversation with whoever's on the other end, now lets you drop in on all your household Echo devices at the same time, perfect for holding a group chat. On a related note, you can now set some of all of your Alexa reminders to sound off on all your Echo devices at once. For those who are new to Alexa, "Drop in" is a feature that essentially turns your Echo device into an intercom, allowing you to connect to another Echo speaker or display on your home network and either listen in or hold a two-way conversation.

Today, Artificial Intelligence (AI) is on everyone's' mind. Whenever we talk about smartphones, the first thing that comes to our mind is responsive to personal assistants. This is because these AI assistants are making our lives easier and businesses are always trying to add new features in their mobile apps. AI is also helping developers in building cutting edge mobile applications that make different processes for its users hassle-free. The Mobile AI market will leap to $17.83 billion in 2023 (up from $5.11 billion in 2018), according to Market and Markets – DZone.

Artificial intelligence has arrived at the inflection point where it's to a lesser degree a pattern than a core ingredient across for all intents and purposes of computing. These organizations are applying the technology to everything from getting strokes recognizing water leaks to understanding fast-food orders. What's more, some of them are planning the AI-prepared chips that will release much increasingly algorithmic developments in the years to come. Let's look at some incredible AI companies where you can unleash your potential Trade giant Amazon has put resources into both the consumer-oriented side of AI and in applications for organizations and their procedures. Alexa, the organization's AI language assistant, integrated into its echo speaker series, is notable around the world.

Graph Convolutional Networks (GCNs) and their variants have received significant attention and achieved start-of-the-art performances on various recommendation tasks. However, many existing GCN models tend to perform recursive aggregations among all related nodes, which arises severe computational burden. Moreover, they favor multi-layer architectures in conjunction with complicated modeling techniques. Though effective, the excessive amount of model parameters largely hinder their applications in real-world recommender systems. To this end, in this paper, we propose the single-layer GCN model which is able to achieve superior performance along with remarkably less complexity compared with existing models. Our main contribution is three-fold. First, we propose a principled similarity metric named distribution-aware similarity (DA similarity), which can guide the neighbor sampling process and evaluate the quality of the input graph explicitly. We also prove that DA similarity has a positive correlation with the final performance, through both theoretical analysis and empirical simulations. Second, we propose a simplified GCN architecture which employs a single GCN layer to aggregate information from the neighbors filtered by DA similarity and then generates the node representations. Moreover, the aggregation step is a parameter-free operation, such that it can be done in a pre-processing manner to further reduce red the training and inference costs. Third, we conduct extensive experiments on four datasets. The results verify that the proposed model outperforms existing GCN models considerably and yields up to a few orders of magnitude speedup in training, in terms of the recommendation performance.

Many unsupervised representation learning methods belong to the class of similarity learning models. While various modality-specific approaches exist for different types of data, a core property of many methods is that representations of similar inputs are close under some similarity function. We propose EMDE (Efficient Manifold Density Estimator) - a framework utilizing arbitrary vector representations with the property of local similarity to succinctly represent smooth probability densities on Riemannian manifolds. Our approximate representation has the desirable properties of being fixed-size and having simple additive compositionality, thus being especially amenable to treatment with neural networks - both as input and output format, producing efficient conditional estimators. We generalize and reformulate the problem of multi-modal recommendations as conditional, weighted density estimation on manifolds. Our approach allows for trivial inclusion of multiple interaction types, modalities of data as well as interaction strengths for any recommendation setting. Applying EMDE to both top-k and session-based recommendation settings, we establish new state-of-the-art results on multiple open datasets in both uni-modal and multi-modal settings. We release the source code and our own real-world dataset of e-commerce product purchases, with special focus on modeling of the item cold-start problem.