Better Caching in Search Advertising Systems with Rapid Refresh Predictions

Li, Conglong; Andersen, David G.; Fu, Qiang; Elnikety, Sameh; He, Yuxiong

doi:10.1145/3178876.3186176

Cited by 8 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is worth mentioning that all these approaches follow the same trend that Inverted files to assess the efficiency. Remarkable is the approach presented by [14], which deals with response times over log files. Unlike these approaches, we have moved one step further by maintaining queries with the highest popularity, relevant documents, and a set of semantically similar terms to these queries.…”

Section: B Results Cachingmentioning

confidence: 99%

See 1 more Smart Citation

Improving Search Engine Performance Through Dynamic Caching

Gutiérrez-Soto

Palomino

Roa

et al. 2021

2021 40th International Conference of the Chilean Computer Science Society (SCCC)

View full text Add to dashboard Cite

Web search engines process several millions of queries per second over several billions of documents. Without any optimization, this process can be very expensive in terms of processing times. In this regard, appropriate use of computing power is essential. One way to tackle this problem is through the use of caching mechanisms. Keep in mind, most research based on caching mechanisms uses repetitive queries-it means queries syntactically equals-to conform caches. Furthermore, the universe of repetitive queries is small in comparison with a set of similar semantically queries. This paper presents a dynamic cache that relies on an online algorithm, which performs a semantic match between the user's query and queries stored in the cache. Broadly speaking, the algorithm employs a priority queue, where popular queries are stored along with their relevant documents. Empirical results show that our proposed approach improves the response times and precision. Moreover, the use of semantically related keywords proves to be a key contribution that had been overlooked in previous research.

show abstract

Section: B Results Cachingmentioning

confidence: 99%

“…Ayers et al employed Intel's Pin Tool [25] to capture full instructions and data traces from a machine in a steady-state, which serves to real user queries. Li et al [14] built a cache simulator based on the production logs of the Bing advertising system.…”

Section: Priority Queuesmentioning

confidence: 99%

Improving Search Engine Performance Through Dynamic Caching

Gutiérrez-Soto

Palomino

Roa

et al. 2021

2021 40th International Conference of the Chilean Computer Science Society (SCCC)

View full text Add to dashboard Cite

show abstract

“…This exhaustive search is a one-time cost amortized across all online/offline queries as long as there is no change to the database and training vectors. From experience at Microsoft Bing, there could be hundreds of millions of latencysensitive online web search queries per day (that require ANN search) [38,39]. Thus the exhaustive search is a small cost compared to the total latency and computation reduction that the proposed approach can achieve over all queries.…”

Section: 13mentioning

confidence: 99%

Improving Approximate Nearest Neighbor Search through Learned Adaptive Early Termination

Zhang

Andersen

et al. 2020

Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data

Self Cite

View full text Add to dashboard Cite

In applications ranging from image search to recommendation systems, the problem of identifying a set of "similar" real-valued vectors to a query vector plays a critical role. However, retrieving these vectors and computing the corresponding similarity scores from a large database is computationally challenging. Approximate nearest neighbor (ANN) search relaxes the guarantee of exactness for efficiency by vector compression and/or by only searching a subset of database vectors for each query. Searching a larger subset increases both accuracy and latency. State-of-the-art ANN approaches use fixed configurations that apply the same termination condition (the size of subset to search) for all queries, which leads to undesirably high latency when trying to achieve the last few percents of accuracy. We find that due to the index structures and the vector distributions, the number of database vectors that must be searched to find the ground-truth nearest neighbor varies widely among queries. Critically, we further identify that the intermediate search result after a certain amount of search is an important runtime feature that indicates how much more search should be performed. To achieve a better tradeoff between latency and accuracy, we propose a novel approach that adaptively determines

show abstract