Neural Information Processing Systems http://nips.cc/

Neural Information Processing Systems http://nips.cc/

Time Warp: The Gap Between Developers' Ideal vs Actual Workweeks in an AI-Driven Era Sukrit Kumar, Drishti Goel, Thomas Zimmermann, Brian Houck, B. Ashok, Chetan Bansal Georgia Institute of T echnology, Microsoft, Microsoft Research, University of California, Irvine Abstract --Software developers balance a variety of different tasks in a workweek, yet the allocation of time often differs from what they consider ideal. Identifying and addressing these deviations is crucial for organizations aiming to enhance the productivity and well-being of the developers. In this paper, we present the findings from a survey of 484 software developers at Microsoft, which aims to identify the key differences between how developers would like to allocate their time during an ideal workweek versus their actual workweek. Our analysis reveals significant deviations between a developer's ideal workweek and their actual workweek, with a clear correlation: as the gap between these two workweeks widens, we observe a decline in both productivity and satisfaction. By examining these deviations in specific activities, we assess their direct impact on the developers' satisfaction and productivity. Additionally, given the growing adoption of AI tools in software engineering, both in the industry and academia, we identify specific tasks and areas that could be strong candidates for automation. In this paper, we make three key contributions: 1) We quantify the impact of workweek deviations on developer productivity and satisfaction 2) We identify individual tasks that disproportionately affect satisfaction and productivity 3) We provide actual data-driven insights to guide future AI automation efforts in software engineering, aligning them with the developers' requirements and ideal workflows for maximizing their productivity and satisfaction. I NTRODUCTION In software engineering, the productivity and satisfaction of developers are pivotal factors that influence both individual performance, customer experience and ultimately, organizational success [1], [2]. The day-to-day activities which define a developer's workweek encompass a broad spectrum of tasks; from coding and designing new systems, to preparing documents, attending meetings, on-boarding new employees, adhering to security and compliance tasks, etc [3]. Each of these tasks is integral to the software development life cycle. Ideally, developers would prefer to allocate their time across these tasks in a way that optimizes both productivity and satisfaction-- this can be referred to as their'ideal workweek'. However, in practice, their'actual workweek', can vary significantly from their'ideal' due to fluctuating workloads, shifting organizational priorities, dependencies on other teams, technical challenges, the influence of the work environment, etc [4], [5], [6].

The canonical setup is the primary approach adopted in cell-free multiple-input multiple-output (MIMO) networks, in which all access points (APs) jointly serve every user equipment (UE). This approach is not scalable in terms of computational complexity and fronthaul signaling becoming impractical in large networks. This work adopts a user-centric approach, a scalable alternative in which only a set of preferred APs jointly serve a UE. Forming the optimal cluster of APs for each UE is a challenging task, especially, when it needs to be dynamically adjusted to meet the quality of service (QoS) requirements of the UE. This complexity is even exacerbated when considering the constrained fronthaul capacity of the UE and the AP. We solve this problem with a novel many-to-many matching game. More specifically, we devise an early acceptance matching algorithm, which immediately admits or rejects UEs based on their requests and available radio resources. The proposed solution significantly reduces the fronthaul signaling while satisfying the maximum of UEs in terms of requested QoS compared to state-of-the-art approaches.

The design and optimization of wireless networks have mostly been based on strong mathematical and theoretical modeling. Nonetheless, as novel applications emerge in the era of 5G and beyond, unprecedented levels of complexity will be encountered in the design and optimization of the network. As a result, the use of Artificial Intelligence (AI) is envisioned for wireless network design and optimization due to the flexibility and adaptability it offers in solving extremely complex problems in real-time. One of the main future applications of AI is enabling user-level personalization for numerous use cases. AI will revolutionize the way we interact with computers in which computers will be able to sense commands and emotions from humans in a non-intrusive manner, making the entire process transparent to users. By leveraging this capability, and accelerated by the advances in computing technologies, wireless networks can be redesigned to enable the personalization of network services to the user level in real-time. While current wireless networks are being optimized to achieve a predefined set of quality requirements, the personalization technology advocated in this article is supported by an intelligent big data-driven layer designed to micro-manage the scarce network resources. This layer provides the intelligence required to decide the necessary service quality that achieves the target satisfaction level for each user. Due to its dynamic and flexible design, personalized networks are expected to achieve unprecedented improvements in optimizing two contradicting objectives in wireless networks: saving resources and improving user satisfaction levels.

Deep reinforcement learning (DRL) has been increasingly employed to handle the dynamic and complex resource management in network slicing. The deployment of DRL policies in real networks, however, is complicated by heterogeneous cell conditions. In this paper, we propose a novel transfer learning (TL) aided multi-agent deep reinforcement learning (MADRL) approach with inter-agent similarity analysis for inter-cell inter-slice resource partitioning. First, we design a coordinated MADRL method with information sharing to intelligently partition resource to slices and manage inter-cell interference. Second, we propose an integrated TL method to transfer the learned DRL policies among different local agents for accelerating the policy deployment. The method is composed of a new domain and task similarity measurement approach and a new knowledge transfer approach, which resolves the problem of from whom to transfer and how to transfer. We evaluated the proposed solution with extensive simulations in a system-level simulator and show that our approach outperforms the state-of-the-art solutions in terms of performance, convergence speed and sample efficiency. Moreover, by applying TL, we achieve an additional gain over 27% higher than the coordinate MADRL approach without TL.

Network slicing enables operators to efficiently support diverse applications on a common physical infrastructure. The ever-increasing densification of network deployment leads to complex and non-trivial inter-cell interference, which requires more than inaccurate analytic models to dynamically optimize resource management for network slices. In this paper, we develop a DIRP algorithm with multiple deep reinforcement learning (DRL) agents to cooperatively optimize resource partition in individual cells to fulfill the requirements of each slice, based on two alternative reward functions. Nevertheless, existing DRL approaches usually tie the pretrained model parameters to specific network environments with poor transferability, which raises practical deployment concerns in large-scale mobile networks. Hence, we design a novel transfer learning-aided DIRP (TL-DIRP) algorithm to ease the transfer of DIRP agents across different network environments in terms of sample efficiency, model reproducibility, and algorithm scalability. The TL-DIRP algorithm first centrally trains a generalized model and then transfers the "generalist" to each local agent as "specialist" with distributed finetuning and execution. TL-DIRP consists of two steps: 1) centralized training of a generalized distributed model, 2) transferring the "generalist" to each "specialist" with distributed finetuning and execution. The numerical results show that not only DIRP outperforms existing baseline approaches in terms of faster convergence and higher reward, but more importantly, TL-DIRP significantly improves the service performance, with reduced exploration cost, accelerated convergence rate, and enhanced model reproducibility. As compared to a traffic-aware baseline, TL-DIRP provides about 15% less violation ratio of the quality of service (QoS) for the worst slice service and 8.8% less violation on the average service QoS.

Current communication networks use design methodologies that prevent the realization of maximum network efficiency. In the first place, while users' perception of satisfactory service diverges widely, current networks are designed to be a "universal fit," where they are generally over-engineered to deliver services appealing to all types of users. Also, current networks lack user-level data cognitive intelligence that would enable fast personalized network decisions and actions through automation. Thus, in this article, we propose the utilization of AI, big data analytics, and real-time non-intrusive user feedback in order to enable the personalization of wireless networks. Based on each user's actual QoS requirements and context, a multi-objective formulation enables the network to micro-manage and optimize the provided QoS and user satisfaction levels simultaneously. Moreover, in order to enable user feedback tracking and measurement, we propose a user satisfaction model based on the zone of tolerance concept. Furthermore, we propose a big-data-driven and AI-based personalization framework to integrate personalization into wireless networks. Finally, we implement a personalized network prototype to demonstrate the proposed personalization concept and its potential benefits through a case study. The case study shows how personalization can be realized to enable the efficient optimization of network resources such that certain requirement levels of user satisfaction and revenue in the form of saved resources are achieved.

Group work is a prevalent activity in educational settings, where students are often divided into topic-specific groups based on their preferences. The grouping should reflect the students' aspirations as much as possible. Usually, the resulting groups should also be balanced in terms of protected attributes like gender or race since studies indicate that students might learn better in a diverse group. Moreover, balancing the group cardinalities is also an essential requirement for fair workload distribution across the groups. In this paper, we introduce the multi-fair capacitated (MFC) grouping problem that fairly partitions students into non-overlapping groups while ensuring balanced group cardinalities (with a lower bound and an upper bound), and maximizing the diversity of members in terms of protected attributes. We propose two approaches: a heuristic method and a knapsack-based method to obtain the MFC grouping. The experiments on a real dataset and a semi-synthetic dataset show that our proposed methods can satisfy students' preferences well and deliver balanced and diverse groups regarding cardinality and the protected attribute, respectively.

We introduce a game-theoretic approach to the study of recommendation systems with strategic content providers. Such systems should be fair and stable. Showing that traditional approaches fail to satisfy these requirements, we propose the Shapley mediator. We show that the Shapley mediator satisfies the fairness and stability requirements, runs in linear time, and is the only economically efficient mechanism satisfying these properties.