Related papers: External-Memory Multimaps
This work introduces the Eigen Memory Tree (EMT), a novel online memory model for sequential learning scenarios. EMTs store data at the leaves of a binary tree and route new samples through the structure using the principal components of…
Cuckoo hashing with a stash is a robust multiple choice hashing scheme with high memory utilization that can be used in many network device applications. Unfortunately, for memory loads beyond 0.5, little is known on its performance. In…
Associative memories are structures that store data patterns and retrieve them given partial inputs. Sparse Clustered Networks (SCNs) are recently-introduced binary-weighted associative memories that significantly improve the storage and…
Data format reverse engineering commonly involves identifying conserved format motifs. However, this process typically requires establishing a common ordering for format elements across instances, particularly for formats using…
Bilingual word embeddings have been widely used to capture the similarity of lexical semantics in different human languages. However, many applications, such as cross-lingual semantic search and question answering, can be largely benefited…
A customer service platform system with a core text semantic similarity (STS) task faces two urgent challenges: Firstly, one platform system needs to adapt to different domains of customers, i.e., different domains adaptation (DDA).…
Recent years have seen more and more demand for a unified framework to address multiple realistic image retrieval tasks concerning both category and attributes. Considering the scale of modern datasets, hashing is favorable for its low…
Entities, as important carriers of real-world knowledge, play a key role in many NLP tasks. We focus on incorporating entity knowledge into an encoder-decoder framework for informative text generation. Existing approaches tried to index,…
Document retrieval for tasks such as search and retrieval-augmented generation typically involves datasets that are unstructured: free-form text without explicit internal structure in each document. However, documents can have a structured…
Machine learning about language can be improved by supplying it with specific knowledge and sources of external information. We present here a new version of the linked open data resource ConceptNet that is particularly well suited to be…
In this paper we describe data structures for orthogonal range reporting in external memory that support fast update operations. The query costs either match the query costs of the best previously known data structures or differ by a small…
In this paper, we focus on training and evaluating effective word embeddings with both text and visual information. More specifically, we introduce a large-scale dataset with 300 million sentences describing over 40 million images crawled…
The Entropic Associative Memory holds objects in a 2D relation or ``memory plane'' using a finite table as the medium. Memory objects are stored by reinforcing simultaneously the cells used by the cue, implementing a form of Hebb's learning…
Large language models, trained on massive corpora, are prone to verbatim memorization of training data, creating significant privacy and copyright risks. While previous works have proposed various definitions for memorization, many exhibit…
As a big data application, extreme multilabel classification has emerged as an important research topic with applications in ranking and recommendation of products and items. A scalable hybrid distributed and shared memory implementation of…
Hash tables are a ubiquitous class of dictionary data structures. However, standard hash table implementations do not translate well into the external memory model, because they do not incorporate locality for insertions. Iacono and…
Maps are an important source of information in archaeology and other sciences. Users want to search for historical maps to determine recorded history of the political geography of regions at different eras, to find out where exactly…
Multicopy search structures such as log-structured merge (LSM) trees are optimized for high insert/update/delete (collectively known as upsert) performance. In such data structures, an upsert on key $k$, which adds $(k,v)$ where $v$ can be…
Learning high-quality feature embeddings efficiently and effectively is critical for the performance of web-scale machine learning systems. A typical model ingests hundreds of features with vocabularies on the order of millions to billions…
Natural memories are associative, declarative and distributed. Symbolic computing memories resemble natural memories in their declarative character, and information can be stored and recovered explicitly; however, they lack the associative…