Adaptive Offline and Online Similarity-Based Caching

Zhou, Jizhe; Simeone, Osvaldo; Zhang, Xing; Wang, Wenbo

doi:10.1109/lnet.2020.3031961

Cited by 17 publications

(12 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the second category of studies, recommendation is utilized to satisfy a request when the requested content is not available in the cache, by recommending some other cached and related contents [6], [7], [8], [26], [27], [28]. The idea of recommending related contents in case of a cache miss is formally introduced in [6] where the authors referred to the scenario as "soft cache hit".…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Optimal Content Caching and Recommendation with Age of Information

Ahani¹,

Yuan²

2021

Preprint

View full text Add to dashboard Cite

Content caching at the network edge has been considered an effective way of mitigating backhaul load and improving user experience. Caching efficiency can be enhanced by content recommendation and by keeping the information fresh. To the best of our knowledge, there is no work that jointly takes into account these aspects. By content recommendation, a requested content that is not in the cache can be alternatively satisfied by a related cached content recommended by the system. Information freshness can be quantified by age of information (AoI). We address, optimal scheduling of cache updates for a time-slotted system accounting for content recommendation and AoI. For each content, there are requests that need to be satisfied, and there is a cost function capturing the freshness of information. We present the following contributions. First, we prove that the problem is NP-hard. Second, we derive an integer linear formulation, by which the optimal solution can be obtained for small-scale scenarios. Third, we develop an algorithm based on Lagrangian decomposition. Fourth, we develop efficient algorithms for solving the resulting subproblems. Our algorithm computes a bound that can be used to evaluate the performance of any suboptimal solution. Finally, we conduct simulations to show the effectiveness of our algorithm in comparison to a greedy schedule.

show abstract

Section: Related Workmentioning

confidence: 99%

“…In [27], the authors try to find the best caching policy for a sequence of requests where recommendation is accounted for. In [28] a multi-hop cache network is studied where soft cache hit is allowed in one of the caches along the path to the end node that stores the initially requested content.…”

Section: Related Workmentioning

confidence: 99%

Optimal Content Caching and Recommendation with Age of Information

Ahani¹,

Yuan²

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Other papers [3]- [6], [20], [22] present more a high-level view of the different components of the specific application system, without specific contributions in terms of cache management policies (e.g., they apply minor changes to exact caching policies like LRU or LFU). Some recent papers [17], [23], [24] propose online caching policies that try to minimize the total cost of the system (the sum of the dissimilarity cost and the fetching cost), but their schemes apply only to the case k = 1, which is of limited practical interest.…”

Section: Similarity Cachesmentioning

confidence: 99%

“…More recently, the authors of [24] have proposed a gradient method to refine the allocation of objects stored by traditional similarity caching policies like SIM-LRU. Similarly, the reference [34] considers a heuristic based on the gradient descent/ascent algorithm to allocate objects in a network of similarity caches. In both papers, the system provides a single similar content (k = 1).…”

Section: Other Relevant Backgroundmentioning

confidence: 99%

Ascent Similarity Caching with Approximate Indexes

Salem¹,

Neglia²,

Carra³

2021

Preprint

View full text Add to dashboard Cite

Similarity search is a key operation in multimedia retrieval systems and recommender systems, and it will play an important role also for future machine learning and augmented reality applications. When these systems need to serve large objects with tight delay constraints, edge servers close to the enduser can operate as similarity caches to speed up the retrieval. In this paper we present AC ¸AI, a new similarity caching policy which improves on the state of the art by using (i) an (approximate) index for the whole catalog to decide which objects to serve locally and which to retrieve from the remote server, and (ii) a mirror ascent algorithm to update the set of local objects with strong guarantees even when the request process does not exhibit any statistical regularity.

show abstract

“…Similarity caching was applied to a number of applications including contextual advertising, object recognition, and recommender systems (see [13] for specific references). To the best of our knowledge, the literature on similarity caching has restricted itself to (i) a single cache (with the exception of [?, 14,15]) and (ii) homogeneous items with identical resource requirements (iii) a serving model without overloading. A consequence is that in our setting similarity caching policies would only allocate models based on their accuracy, ignoring the trade-offs imposed by their resource requirements.…”

Section: Related Workmentioning

confidence: 99%

Towards Inference Delivery Networks: Distributing Machine Learning with Optimality Guarantees

Salem¹,

Castellano²,

Neglia³

et al. 2021

Preprint

View full text Add to dashboard Cite

We present the novel idea of inference delivery networks (IDN), networks of computing nodes that coordinate to satisfy inference requests achieving the best trade-off between latency and accuracy. IDNs bridge the dichotomy between device and cloud execution by integrating inference delivery at the various tiers of the infrastructure continuum (access, edge, regional data center, cloud). We propose a distributed dynamic policy for ML model allocation in an IDN by which each node periodically updates its local set of inference models based on requests observed during the recent past plus limited information exchange with its neighbor nodes. Our policy offers strong performance guarantees in an adversarial setting and shows improvements over greedy heuristics with similar complexity in realistic scenarios.

show abstract

Adaptive Offline and Online Similarity-Based Caching

Cited by 17 publications

References 9 publications

Optimal Content Caching and Recommendation with Age of Information

Optimal Content Caching and Recommendation with Age of Information

Ascent Similarity Caching with Approximate Indexes

Towards Inference Delivery Networks: Distributing Machine Learning with Optimality Guarantees

Contact Info

Product

Resources

About