Singularity
Singularity is a container platform focused on supporting ‘Mobility of Compute’. Mobility of Compute encapsulates the development to compute model where developers can work in an environment of their choosing and creation, and when the developer needs additional compute resources, this environment can easily be copied and executed on other platforms. Additionally, as the primary use case for Singularity is targeted towards computational portability. Many of the barriers to entry of other container solutions do not apply to Singularity, making it an ideal solution for users (both computational and non-computational) and HPC centers. …

relative Age of Information (rAoI)
In this paper, we introduce a new data freshness metric, relative Age of Information (rAoI), and examine it in a single server system with various packet management schemes. The (classical) AoI metric was introduced to measure the staleness of status updates at the receiving end with respect to their generation at the source. This metric addresses systems where the timings of update generation at the source are absolute and can be designed separately or jointly with the transmission schedules. In many decentralized applications, transmission schedules are blind to update generation timing, and the transmitter can know the timing of an update packet only after it arrives. As such, an update becomes stale after a new one arrives. The rAoI metric measures how fresh the data is at the receiver with respect to the data at the transmitter. It introduces a particularly explicit dependence on the arrival process in the evaluation of age. We investigate several queuing disciplines and provide closed form expressions for rAoI and numerical comparisons. …

Asynchronous Episodic Deep Deterministic Policy Gradient (AE-DDPG)
Deep Deterministic Policy Gradient (DDPG) has been proved to be a successful reinforcement learning (RL) algorithm for continuous control tasks. However, DDPG still suffers from data insufficiency and training inefficiency, especially in computationally complex environments. In this paper, we propose Asynchronous Episodic Deep Deterministic Policy Gradient (AE-DDPG), as an expansion of DDPG, which can achieve more effective learning with less training time required. First, we design a modified scheme for data collection in an asynchronous fashion. Generally, for asynchronous RL algorithms, sample efficiency or/and training stability diminish as the degree of parallelism increases. We consider this problem from the perspectives of both data generation and data utilization. In detail, we re-design experience replay by introducing the idea of episodic control so that the agent can latch on good trajectories rapidly. In addition, we also inject a new type of noise in action space to enrich the exploration behaviors. Experiments demonstrate that our AE-DDPG achieves higher rewards and requires less time consuming than most popular RL algorithms in Learning to Run task which has a computationally complex environment. Not limited to the control tasks in computationally complex environments, AE-DDPG also achieves higher rewards and 2- to 4-fold improvement in sample efficiency on average compared to other variants of DDPG in MuJoCo environments. Furthermore, we verify the effectiveness of each proposed technique component through abundant ablation study. …

Relational Collaborative Filtering
Existing item-based collaborative filtering (ICF) methods leverage only the relation of collaborative similarity. Nevertheless, there exist multiple relations between items in real-world scenarios. Distinct from the collaborative similarity that implies co-interact patterns from the user perspective, these relations reveal fine-grained knowledge on items from different perspectives of meta-data, functionality, etc. However, how to incorporate multiple item relations is less explored in recommendation research. In this work, we propose Relational Collaborative Filtering (RCF), a general framework to exploit multiple relations between items in recommender system. We find that both the relation type and the relation value are crucial in inferring user preference. To this end, we develop a two-level hierarchical attention mechanism to model user preference. The first-level attention discriminates which types of relations are more important, and the second-level attention considers the specific relation values to estimate the contribution of a historical item in recommending the target item. To make the item embeddings be reflective of the relational structure between items, we further formulate a task to preserve the item relations, and jointly train it with the recommendation task of preference modeling. Empirical results on two real datasets demonstrate the strong performance of RCF. Furthermore, we also conduct qualitative analyses to show the benefits of explanations brought by the modeling of multiple item relations. …