Increasing demand from AI/ML workloads is exacerbating the rising energy consumption of data centers. Recent advances in hardware such as NVIDIA's Multi Instance GPUs (MIGs) offer improvements in flexibility and computational power and the opportunity for data centers to manage incoming jobs in energy-efficient ways, while maintaining acceptable performance. The challenge in achieving this multi-objective in a MIG environment through job scheduling is multi-faceted. Firstly, for a given MIG configuration, one seeks an easy-toimplement scheduling algorithm which selects a job from the queue as well as decides on which slice in the configuration the job runs. Secondly, for the identified scheduling algorithm, a particular MIG configuration may not always be suitable (as the workload fluctuates) and may need to be repartitioned. We tackle both problems using simulations and reinforcement learning (RL). We present a dynamic repartitioning scheduling framework for a single MIG as a solution to a multi-objective heterogeneous machine scheduling problem with preemption. In particular, we compare four scheduling algorithms and identify a promising one. Then, we employ reinforcement learning to perform dynamic repartitioning over a day. Furthermore, using a diurnal workload pattern based on real-world data center traces, we demonstrate the superiority of our dynamic repartitioning algorithm over twice-daily repartitioning (26%), static partitioning (31%) and no partitioning at all (68%) according to a multi-objective function of energy consumption and tardiness. Our results indicate specific preferred configurations at different times of the day under different queue conditions, suggesting a policy for predictive and automatic reconfiguration.

As Approximate Nearest Neighbor Search (ANNS)-based dense retrieval becomes ubiquitous for search and recommendation scenarios, efficiently answering filtered ANNS queries has become a critical requirement. Filtered ANNS queries ask for the nearest neighbors of a query’s embedding from the points in the index that match the query’s labels such as date, price range, language. There has been little prior work on algorithms that use label metadata associated with vector data to build efficient indices for filtered ANNS queries. Consequently, current indices have high search latency or low recall which is not practical in interactive web-scenarios. We present two algorithms with native support for faster and more accurate filtered ANNS queries: one with streaming support, and another based on batch construction. Central to our algorithms is the construction of a graph-structured index which forms connections not only based on the geometry of the vector data, but also the associated label set. On real-world data with natural labels, both algorithms are an order of magnitude or more efficient for filtered queries than the current state of the art algorithms. The generated indices also be queried from an SSD and support thousands of queries per second at over recall@10.

We propose INDEPROP, a novel Natural Language Processing (NLP) application for combating online disinformation by mitigating propaganda from news articles. INDEPROP (Information-Preserving De-propagandization) involves fine-grained propaganda detection and its removal while maintaining document level coherence, grammatical correctness and most importantly, preserving the news articles’ information content. We curate the first large-scale dataset of its kind consisting of around 1M tokens. We also propose a set of automatic evaluation metrics for the same and observe its high correlation with human judgment. Furthermore, we show that fine-tuning the existing propaganda detection systems on our dataset considerably improves their generalization to the test set.

Compiling the votes of a subelectorate consists of storing the votes of a subset of voters in a compressed form, such that the winners can still be determined when additional votes are included. This leads to the notion of compilation complexity, which has already been investigated for single-winner voting rules. We perform a compilation complexity analysis of several common multi-winner voting rules.