Related papers: Tail-Tolerant Distributed Search

Learned sparse models such as SPLADE have successfully shown how to incorporate the benefits of state-of-the-art neural information retrieval models into the classical inverted index data structure. Despite their improvements in…

Application tail latency is a key metric for many services, with high latencies being linked directly to loss of revenue. Modern deeply-nested micro-service architectures exacerbate tail latencies, increasing the likelihood of users…

Similarity-based vector search facilitates many important applications such as search and recommendation but is limited by the memory capacity and bandwidth of a single machine due to large datasets and intensive data read. In this paper,…

Reinforcement fine-tuning (RFT) often suffers from reward over-optimization, where a policy model hacks the reward signals to achieve high scores while producing low-quality outputs. Our theoretical analysis shows that the key lies in…

Multi-task learning (MTL) aims to make full use of the knowledge contained in multi-task supervision signals to improve the overall performance. How to make the knowledge of multiple tasks shared appropriately is an open problem for MTL.…

Retrieval-Augmented Generation (RAG) is a crucial method for mitigating hallucinations in Large Language Models (LLMs) and integrating external knowledge into their responses. Existing RAG methods typically employ query rewriting to clarify…

Deep networks allow to obtain outstanding results in semantic segmentation, however they need to be trained in a single shot with a large amount of data. Continual learning settings where new classes are learned in incremental steps and…

Modern computationally-intensive applications often operate under time constraints, necessitating acceleration methods and distribution of computational workloads across multiple entities. However, the outcome is either achieved within the…

Crowdsourcing and data mining can be used to effectively reduce the effort associated with the partial replication and enhancement of qualitative studies. For example, in a primary study, other researchers explored factors influencing the…

Long-Tailed Semi-Supervised Learning (LTSSL) aims to learn from class-imbalanced data where only a few samples are annotated. Existing solutions typically require substantial cost to solve complex optimization problems, or class-balanced…

This paper considers the task of performing binary search under noisy decisions, focusing on the application of target area localization. In the presence of noise, the classical partitioning approach of binary search is prone to error…

Query rewriting is essential for database performance optimization, but existing automated rule enumeration methods suffer from exponential search spaces, severe redundancy, and poor scalability, especially when handling complex query plans…

Differentiable architecture search (DARTS) is an effective method for data-driven neural network design based on solving a bilevel optimization problem. Despite its success in many architecture search tasks, there are still some concerns…

Differentiable neural architecture search (DARTS) has gained much success in discovering flexible and diverse cell types. To reduce the evaluation gap, the supernet is expected to have identical layers with the target network. However, even…

Large language models (LLMs) have notably progressed in multi-step and long-chain reasoning. However, extending their reasoning capabilities to encompass deep interactions with search remains a non-trivial challenge, as models often fail to…

In data centers, data replication is the primary method used to ensure availability of customer data. To avoid correlated failure, cloud storage infrastructure providers model hierarchical failure domains using a tree, and avoid placing a…

Sequential recommendation (SR) learns user preferences based on their historical interaction sequences and provides personalized suggestions. In real-world scenarios, most users can only interact with a handful of items, while the majority…

We propose a novel application of coded computing to the problem of the nearest neighbor estimation using MatDot Codes [Fahim. et.al. 2017], that are known to be optimal for matrix multiplication in terms of recovery threshold under storage…

Information retrieval is a core component of many intelligent systems as it enables conditioning of outputs on new and large-scale datasets. While effective, the standard practice of encoding data into high-dimensional representations for…

State of the art image retrieval performance is achieved with CNN features and manifold ranking using a k-NN similarity graph that is pre-computed off-line. The two most successful existing approaches are temporal filtering, where manifold…