Related papers: Tail-Tolerant Distributed Search
We frame code generation as a black-box optimization problem within the code space and demonstrate how optimization-inspired techniques can enhance inference scaling. Based on this perspective, we propose SCATTERED FOREST SEARCH (SFS), a…
Although the bipartite shopping graphs are straightforward to model search behavior, they suffer from two challenges: 1) The majority of items are sporadically searched and hence have noisy/sparse query associations, leading to a…
Sparse recovery and subset selection are fundamental problems in varied communities, including signal processing, statistics and machine learning. Herein, we focus on an important greedy algorithm for these problems: Backward Stepwise…
In edge computing, emerging network slicing and computation offloading can support Edge Service Providers (ESPs) better handling diverse distributions of user requests, to improve Quality-of-Service (QoS) and resource efficiency. However,…
Diffusion is commonly used as a ranking or re-ranking method in retrieval tasks to achieve higher retrieval performance, and has attracted lots of attention in recent years. A downside to diffusion is that it performs slowly in comparison…
Self-supervised learning (SSL) as an effective paradigm of representation learning has achieved tremendous success on various curated datasets in diverse scenarios. Nevertheless, when facing the long-tailed distribution in real-world…
Similarity search is critical for many database applications, including the increasingly popular online services for Content-Based Multimedia Retrieval (CBMR). These services, which include image search engines, must handle an overwhelming…
With the widespread use of shared-nothing clusters of servers, there has been a proliferation of distributed object stores that offer high availability, reliability and enhanced performance for MapReduce-style workloads. However, relational…
Web-scale search systems typically tackle the scalability challenge with a two-step paradigm: retrieval and ranking. The retrieval step, also known as candidate selection, often involves extracting standardized entities, creating an…
Retrieval-Augmented Generation (RAG) based on Large Language Models (LLMs) is a powerful solution to understand and query the industry's closed-source documents. However, basic RAG often struggles with complex QA tasks in legal and…
Response retrieval is a subset of neural ranking in which a model selects a suitable response from a set of candidates given a conversation history. Retrieval-based chat-bots are typically employed in information seeking conversational…
This paper introduces the concept of size-aware sharding to improve tail latencies for in-memory key-value stores, and describes its implementation in the Minos key-value store. Tail latencies are crucial in distributed applications with…
Runtime performance variability at the servers has been a major issue, hindering the predictable and scalable performance in modern distributed systems. Executing requests or jobs redundantly over multiple servers has been shown to be…
Dataset distillation (DD) aims to compress large-scale datasets into compact synthetic counterparts for efficient model training. However, existing DD methods exhibit substantial performance degradation on long-tailed datasets. We identify…
Language models (LMs) now excel at many tasks such as few-shot learning, question answering, reasoning, and dialog. However, they sometimes generate unsupported or misleading content. A user cannot easily determine whether their outputs are…
Edge networks are promising to provide better services to users by provisioning computing and storage resources at the edge of networks. However, due to the uncertainty and diversity of user interests, content popularity, distributed…
Analysts commonly investigate the data distributions derived from statistical aggregations of data that are represented by charts, such as histograms and binned scatterplots, to visualize and analyze a large-scale dataset. Aggregate queries…
Analyzing large scale data has emerged as an important activity for many organizations in the past few years. This large scale data analysis is facilitated by the MapReduce programming and execution model and its implementations, most…
Despite recent advancements in out-of-distribution (OOD) detection, most current studies assume a class-balanced in-distribution training dataset, which is rarely the case in real-world scenarios. This paper addresses the challenging task…
Tree of Thoughts (ToT) enhances Large Language Model (LLM) reasoning by structuring problem-solving as a spanning tree. However, recent methods focus on search accuracy while overlooking computational efficiency. The challenges of…