Applied recommender systems research is in a curious position. While there is a very rigorous protocol for measuring performance by A/B testing, best practice for finding a `B' to test does not explicitly target performance but rather targets a proxy measure. The success or failure of a given A/B test then depends entirely on if the proposed proxy is better correlated to performance than the previous proxy. No principle exists to identify if one proxy is better than another offline, leaving the practitioners shooting in the dark. The purpose of this position paper is to question this anti-Utopian thinking and argue that a non-standard use of the deep learning stacks actually has the potential to unlock reward optimizing recommendation.

The ability to shape health behaviors of large populations automatically, across wearable types and disease conditions at scale has tremendous potential to improve global health outcomes. We designed and implemented an AI driven platform for digital algorithmic nudging, enabled by a Graph-Neural Network (GNN) based Recommendation System, and granular health behavior data from wearable fitness devices. Here we describe the efficacy results of this platform with its capabilities of personalized and contextual nudging to $n=84,764$ individuals over a 12-week period in Singapore. We statistically validated that participants in the target group who received such AI optimized daily nudges increased daily physical activity like step count by 6.17% ($p = 3.09\times10^{-4}$) and weekly minutes of Moderate to Vigorous Physical Activity (MVPA) by 7.61% ($p = 1.16\times10^{-2}$), compared to matched participants in control group who did not receive any nudges. Further, such nudges were very well received, with a 13.1% of nudges sent being opened (open rate), and 11.7% of the opened nudges rated useful compared to 1.9% rated as not useful thereby demonstrating significant improvement in population level engagement metrics.

Collaborator recommendation is an important task in academic domain. Most of the existing approaches have the assumption that the recommendation system only need to recommend a specific researcher for the task. However, academic successes can be owed to productive collaboration of a whole academic team. In this work, we propose a new task: academic team worker recommendation: with a given status: student, assistant professor or prime professor, research interests and specific task, we can recommend an academic team formed as (prime professor, assistant professor, student). For this task, we propose a model CQBG-R(Citation-Query Blended Graph-Ranking). The key ideas is to combine the context of the query and the papers with the graph topology to form a new graph(CQBG), which can target at the research interests and the specific research task for this time. The experiment results show the effectiveness of the proposed method.

Fine-tuning is becoming widely used for leveraging the power of pre-trained foundation models in new downstream tasks. While there are many successes of fine-tuning on various tasks, recent studies have observed challenges in the generalization of fine-tuned models to unseen distributions (i.e., out-of-distribution; OOD). To improve OOD generalization, some previous studies identify the limitations of fine-tuning data and regulate fine-tuning to preserve the general representation learned from pre-training data. However, potential limitations in the pre-training data and models are often ignored. In this paper, we contend that overly relying on the pre-trained representation may hinder fine-tuning from learning essential representations for downstream tasks and thus hurt its OOD generalization. It can be especially catastrophic when new tasks are from different (sub)domains compared to pre-training data. To address the issues in both pre-training and fine-tuning data, we propose a novel generalizable fine-tuning method LEVI, where the pre-trained model is adaptively ensembled layer-wise with a small task-specific model, while preserving training and inference efficiencies. By combining two complementing models, LEVI effectively suppresses problematic features in both the fine-tuning data and pre-trained model and preserves useful features for new tasks. Broad experiments with large language and vision models show that LEVI greatly improves fine-tuning generalization via emphasizing different views from fine-tuning data and pre-trained features.

Spoken dialogue systems have transformed human-machine interaction by providing real-time responses to queries. However, misunderstandings between the user and system persist. This study explores the significance of interactional language in dialogue repair between virtual assistants and users by analyzing interactions with Google Assistant and Siri, focusing on their utilization and response to the other-initiated repair strategy "huh?" prevalent in human-human interaction. Findings reveal several assistant-generated strategies but an inability to replicate human-like repair strategies such as "huh?". English and Spanish user acceptability surveys show differences in users' repair strategy preferences and assistant usage, with both similarities and disparities among the two surveyed languages. These results shed light on inequalities between interactional language in human-human interaction and human-machine interaction, underscoring the need for further research on the impact of interactional language in human-machine interaction in English and beyond.

Ryan and Randy met at a sex party in 2019 and started dating shortly after. By month four, they made the relationship official, eventually moved into a two-story house in Los Angeles together, and did all the things happy couples do: date nights, vacation with friends, support one another's ambitions. Then, in 2022, they decided to open the relationship. As Covid-19 restrictions loosened, "we were being exposed to other attractions and to other people who were seeking our attention," Ryan says. "We both knew we had attractions to other people. It was, let's talk about being open and see what that means for us. Because being open can mean different things to different people."

If you're already onboard with Alexa and have decided you want a smart display, a new deal on Amazon's latest Echo Show 8 may be of interest. The 8-inch display is currently down to 90 at Amazon, Target, Best Buy and other retailers, which matches the lowest price we've seen since the device was unveiled last September. Amazon normally sells the smart display for 150, though we saw it drop to 105 for much of the holiday season. Amazon's offer also includes a Sengled color smart bulb for no extra cost. That bulb is compatible with the Matter smart home standard, and we recommend a similar model in our guide to the best smart lights. This matches the best price we've tracked for the latest iteration of Amazon's 8-inch smart display and includes a smart bulb for no extra cost.

Automated Machine Learning (AutoML) has greatly advanced applications of Machine Learning (ML) including model compression, machine translation, and computer vision. Recommender Systems (RecSys) can be seen as an application of ML. Yet, AutoML has found little attention in the RecSys community; nor has RecSys found notable attention in the AutoML community. Only few and relatively simple Automated Recommender Systems (AutoRecSys) libraries exist that adopt AutoML techniques. However, these libraries are based on student projects and do not offer the features and thorough development of AutoML libraries. We set out to determine how AutoML libraries perform in the scenario of an inexperienced user who wants to implement a recommender system. We compared the predictive performance of 60 AutoML, AutoRecSys, ML, and RecSys algorithms from 15 libraries, including a mean predictor baseline, on 14 explicit feedback RecSys datasets. To simulate the perspective of an inexperienced user, the algorithms were evaluated with default hyperparameters. We found that AutoML and AutoRecSys libraries performed best. AutoML libraries performed best for six of the 14 datasets (43%), but it was not always the same AutoML library performing best. The single-best library was the AutoRecSys library Auto-Surprise, which performed best on five datasets (36%). On three datasets (21%), AutoML libraries performed poorly, and RecSys libraries with default parameters performed best. Although, while obtaining 50% of all placements in the top five per dataset, RecSys algorithms fall behind AutoML on average. ML algorithms generally performed the worst.

In today's data centers, personalized recommendation systems face challenges such as the need for large memory capacity and high bandwidth, especially when performing embedding operations. Previous approaches have relied on DIMM-based near-memory processing techniques or introduced 3D-stacked DRAM to address memory-bound issues and expand memory bandwidth. However, these solutions fall short when dealing with the expanding size of personalized recommendation systems. Recommendation models have grown to sizes exceeding tens of terabytes, making them challenging to run efficiently on traditional single-node inference servers. Although various algorithmic methods have been proposed to reduce embedding table capacity, they often result in increased memory access or inefficient utilization of memory resources. This paper introduces HEAM, a heterogeneous memory architecture that integrates 3D-stacked DRAM with DIMM to accelerate recommendation systems in which compositional embedding is utilized-a technique aimed at reducing the size of embedding tables. The architecture is organized into a three-tier memory hierarchy consisting of conventional DIMM, 3D-stacked DRAM with a base die-level Processing-In-Memory (PIM), and a bank group-level PIM incorporating a Look-Up-Table. This setup is specifically designed to accommodate the unique aspects of compositional embedding, such as temporal locality and embedding table capacity. This design effectively reduces bank access, improves access efficiency, and enhances overall throughput, resulting in a 6.3 times speedup and 58.9% energy savings compared to the baseline.

The use of natural language interfaces in the field of human-computer interaction is undergoing intense study through dedicated scientific and industrial research. The latest contributions in the field, including deep learning approaches like recurrent neural networks, the potential of context-aware strategies and user-centred design approaches, have brought back the attention of the community to software-based dialogue systems, generally known as conversational agents or chatbots. Nonetheless, and given the novelty of the field, a generic, context-independent overview on the current state of research of conversational agents covering all research perspectives involved is missing. Motivated by this context, this paper reports a survey of the current state of research of conversational agents through a systematic literature review of secondary studies. The conducted research is designed to develop an exhaustive perspective through a clear presentation of the aggregated knowledge published by recent literature within a variety of domains, research focuses and contexts. As a result, this research proposes a holistic taxonomy of the different dimensions involved in the conversational agents' field, which is expected to help researchers and to lay the groundwork for future research in the field of natural language interfaces.