I wanted to write this piece once my sadness had faded. I don't think it has really. That feeling has been overtaken by other emotions. Why I have been sad, you ask? Modern Family, just like all good things, inevitably came to an end. You'll learn so much about family, friendships, society, and business just by watching the family comedy series. My most favorite bits of the show were those that highlighted technology in modern society; from the closets that pick out outfits for you depending on the weather, the robot concierge, and Fridget.

Federated recommendation is a new notion of private distributed recommender systems. It aims to address the data silo and privacy problems altogether. Current federated recommender systems mainly utilize homomorphic encryption and differential privacy methods to protect the intermediate computational results. However, the former comes with extra communication and computation costs, the latter damages model accuracy. Neither of them could simultaneously satisfy the real-time feedback and accurate personalization requirements of recommender systems. In this paper, we proposed a new federated recommendation framework, named federated masked matrix factorization. Federated masked matrix factorization could protect the data privacy in federated recommender systems without sacrificing efficiency or efficacy. Instead of using homomorphic encryption and differential privacy, we utilize the secret sharing technique to incorporate the secure aggregation process of federated matrix factorization. Compared with homomorphic encryption, secret sharing largely speeds up the whole training process. In addition, we introduce a new idea of personalized masks and apply it in the proposed federated masked matrix factorization framework. On the one hand, personalized masks could further improve efficiency. On the other hand, personalized masks also benefit efficacy. Empirically, we show the superiority of the designed model on different real-world data sets. Besides, we also provide the privacy guarantee and discuss the extension of the personalized mask method to the general federated learning tasks.

Recent studies in recommender systems have managed to achieve significantly improved performance by leveraging reviews for rating prediction. However, despite being extensively studied, these methods still suffer from some limitations. First, previous studies either encode the document or extract latent sentiment via neural networks, which are difficult to interpret the sentiment of reviewers intuitively. Second, they neglect the personalized interaction of reviews with user/item, i.e., each review has different contributions when modeling the sentiment preference of user/item. To remedy these issues, we propose a Sentiment-aware Interactive Fusion Network (SIFN) for review-based item recommendation. Specifically, we first encode user/item reviews via BERT and propose a light-weighted sentiment learner to extract semantic features of each review. Then, we propose a sentiment prediction task that guides the sentiment learner to extract sentiment-aware features via explicit sentiment labels. Finally, we design a rating prediction task that contains a rating learner with an interactive and fusion module to fuse the identity (i.e., user and item ID) and each review representation so that various interactive features can synergistically influence the final rating score. Experimental results on five real-world datasets demonstrate that the proposed model is superior to state-of-the-art models.

Cross-Domain Recommendation (CDR) and Cross-System Recommendation (CSR) have been proposed to improve the recommendation accuracy in a target dataset (domain/system) with the help of a source one with relatively richer information. However, most existing CDR and CSR approaches are single-target, namely, there is a single target dataset, which can only help the target dataset and thus cannot benefit the source dataset. In this paper, we focus on three new scenarios, i.e., Dual-Target CDR (DTCDR), Multi-Target CDR (MTCDR), and CDR+CSR, and aim to improve the recommendation accuracy in all datasets simultaneously for all scenarios. To do this, we propose a unified framework, called GA (based on Graph embedding and Attention techniques), for all three scenarios. In GA, we first construct separate heterogeneous graphs to generate more representative user and item embeddings. Then, we propose an element-wise attention mechanism to effectively combine the embeddings of common entities (users/items) learned from different datasets. Moreover, to avoid negative transfer, we further propose a Personalized training strategy to minimize the embedding difference of common entities between a richer dataset and a sparser dataset, deriving three new models, i.e., GA-DTCDR-P, GA-MTCDR-P, and GA-CDR+CSR-P, for the three scenarios respectively. Extensive experiments conducted on four real-world datasets demonstrate that our proposed GA models significantly outperform the state-of-the-art approaches.

Artificial intelligence (AI) systems operate in increasingly diverse areas, from healthcare to facial recognition, the stock market, autonomous vehicles, and so on. While the underlying digital infrastructure of AI systems is developing rapidly, each area of implementation is subject to different degrees and processes of legitimization. By combining elements from institutional theory and information systems-theory, this paper presents a conceptual framework to analyze and understand AI-induced field-change. The introduction of novel AI-agents into new or existing fields creates a dynamic in which algorithms (re)shape organizations and institutions while existing institutional infrastructures determine the scope and speed at which organizational change is allowed to occur. Where institutional infrastructure and governance arrangements, such as standards, rules, and regulations, still are unelaborate, the field can move fast but is also more likely to be contested. The institutional infrastructure surrounding AI-induced fields is generally little elaborated, which could be an obstacle to the broader institutionalization of AI-systems going forward.

Collaborative filtering (CF) is a long-standing problem of recommender systems. Many novel methods have been proposed, ranging from classical matrix factorization to recent graph convolutional network-based approaches. After recent fierce debates, researchers started to focus on linear graph convolutional networks (GCNs) with a layer combination, which show state-of-the-art accuracy in many datasets. In this work, we extend them based on neural ordinary differential equations (NODEs), because the linear GCN concept can be interpreted as a differential equation, and present the method of Learnable-Time ODE-based Collaborative Filtering (LT-OCF). The main novelty in our method is that after redesigning linear GCNs on top of the NODE regime, i) we learn the optimal architecture rather than relying on manually designed ones, ii) we learn smooth ODE solutions that are considered suitable for CF, and iii) we test with various ODE solvers that internally build a diverse set of neural network connections. We also present a novel training method specialized to our method. In our experiments with three benchmark datasets, Gowalla, Yelp2018, and Amazon-Book, our method consistently shows better accuracy than existing methods, e.g., a recall of 0.0411 by LightGCN vs. 0.0442 by LT-OCF and an NDCG of 0.0315 by LightGCN vs. 0.0341 by LT-OCF in Amazon-Book. One more important discovery in our experiments that is worth mentioning is that our best accuracy was achieved by dense connections rather than linear connections.

Android TV fans looking for something a bit more powerful than a Chromecast should consider the NVIDIA Shield TV. However, now you can grab the NVIDIA Shield TV for $130, or $20 off its normal price. That's almost a record low -- we saw it drop to $129 ahead of Black Friday last year -- but this is the best price we've seen in 2021, and it's only come around a couple of times so far. Despite being more expensive than streaming dongles of similar size, the NVIDIA Shield is worth the extra money thanks to its Tegra X1 processor. It's powerful enough to run the Android TV platform with ease, and it supports Dolby Vision HDR, Dolby Atmos audio, Chromecast 4K and AI-powered HD-to-4K upscaling. It also works with the Google Assistant and Amazon's Alexa, so you can bark orders at it instead of using the triangular remote if you wish.

I participated in an open-source program LGMSOC-21 as a contributor. I contributed a recommendation system that uses content-based filtering to recommend items to users. It uses item features to filter content. Tokenize features using the count vectorizer this will create a count matrix. Then convert the count matrix into a cosine matrix. Pick up the top items based on the cosine matrix to recommend.

Successful sequential recommendation systems rely on accurately capturing the user's short-term and long-term interest. Although Transformer-based models achieved state-of-the-art performance in the sequential recommendation task, they generally require quadratic memory and time complexity to the sequence length, making it difficult to extract the long-term interest of users. On the other hand, Multi-Layer Perceptrons (MLP)-based models, renowned for their linear memory and time complexity, have recently shown competitive results compared to Transformer in various tasks. Given the availability of a massive amount of the user's behavior history, the linear memory and time complexity of MLP-based models make them a promising alternative to explore in the sequential recommendation task. To this end, we adopted MLP-based models in sequential recommendation but consistently observed that MLP-based methods obtain lower performance than those of Transformer despite their computational benefits. From experiments, we observed that introducing explicit high-order interactions to MLP layers mitigates such performance gap. In response, we propose the Multi-Order Interaction (MOI) layer, which is capable of expressing an arbitrary order of interactions within the inputs while maintaining the memory and time complexity of the MLP layer. By replacing the MLP layer with the MOI layer, our model was able to achieve comparable performance with Transformer-based models while retaining the MLP-based models' computational benefits.

By exploring the various facets of gendering at play in the design of VPAs, specifically Alexa, I argue that gendering Alexa as female poses societal harm insofar as she reproduces normative assumptions about the role of women as submissive, inferior, and secondary to men. The prevalence of AI-driven virtual personal assistants (VPAs) is proliferating, with Amazon Echo being one of the most highly sought-after smart speakers globally. However, not until recently has there been much research or attention focused on the gender bias noticeably programmed into this technology, specifically Alexa, intentionally designed, coded, and programmed by men and gendered to be distinctly female. Big Tech's decision to gender VPAs is seen most evident through their assigned female names and their female voices that users find more pleasant to give orders to than a male voice, as seen through witty flirtatious programmed responses. Through these interactions, Alexa performs gender as a feminized and sexualized entity imposed upon her by her Silicon Valley creators, that has the potential to unravel decades of social and political progress, as well as reinstate the gender bias of the past that women strived to eradicate. In the not-so-distant future, TechCrunch forecasts that the use of voice assistants is set to triple over the next few years and estimates there will be ten billion digital voice assistants by 2023, up from the 2.5 billion assistants in use at the end of 2018. This growth is attributed to Amazon Echo being one of the most highly sought-after smart speakers in the world.