Search Results for author:
Found 33 papers, 12 papers with code
Introducing Graph Smoothness Loss for Training Deep Learning Architectures
We introduce a novel loss function for training deep learning architectures to perform classification.
A Unified Deep Learning Formalism For Processing Graph Signals
Convolutional Neural Networks are very efficient at processing signals defined on a discrete Euclidean space (such as images).
Attention Based Pruning for Shift Networks
In many application domains such as computer vision, Convolutional Layers (CLs) are key to the accuracy of deep learning methods.
Comparing linear structure-based and data-driven latent spatial representations for sequence prediction
Predicting the future of Graph-supported Time Series (GTS) is a key challenge in many domains, such as climate monitoring, finance or neuroimaging.
Structural Robustness for Deep Learning Architectures
Deep Networks have been shown to provide state-of-the-art performance in many machine learning challenges.
Improved Visual Localization via Graph Smoothing
One solution to this problem is to learn a deep neural network to infer the pose of a query image after learning on a dataset of images with known poses.
Deep geometric knowledge distillation with graphs
Specifically we introduce a graph-based RKD method, in which graphs are used to capture the geometry of latent spaces.
Graph topology inference benchmarks for machine learning
Graphs are nowadays ubiquitous in the fields of signal processing and machine learning.
Representing Deep Neural Networks Latent Space Geometries with Graphs
However, when processing a batch of inputs concurrently, the corresponding set of intermediate representations exhibit relations (what we call a geometry) on which desired properties can be sought.
Ranking Deep Learning Generalization using Label Variation in Latent Geometry Graphs
Measuring the generalization performance of a Deep Neural Network (DNN) without relying on a validation set is a difficult task.
DecisiveNets: Training Deep Associative Memories to Solve Complex Machine Learning Problems
Learning deep representations to solve complex machine learning tasks has become the prominent trend in the past few years.
Graphs for deep learning representations
In recent years, Deep Learning methods have achieved state of the art performance in a vast range of machine learning tasks, including image classification and multilingual automatic text translation.
Improving Classification Accuracy with Graph Filtering
In machine learning, classifiers are typically susceptible to noise in the training data.
SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval
Meanwhile, there has been a growing interest in learning \emph{sparse} representations for documents and queries, that could inherit from the desirable properties of bag-of-words models such as the exact matching of terms and the efficiency of inverted indexes.
Ranked #5 on
Zero-shot Text Search
on BEIR
Graphs as Tools to Improve Deep Learning Methods
This chapter is composed of four main parts: tools for visualizing intermediate layers in a DNN, denoising data representations, optimizing graph objective functions and regularizing the learning process.
TLDR: Twin Learning for Dimensionality Reduction
Dimensionality reduction methods are unsupervised approaches which learn low-dimensional spaces where some properties of the initial space, typically the notion of "neighborhood", are preserved.
A Study on Token Pruning for ColBERT
Our experiments show that ColBERT indexes can be pruned up to 30\% on the MS MARCO passage collection without a significant drop in performance.
Composite Code Sparse Autoencoders for first stage retrieval
Second, CCSA can be used as a binary quantization method and we propose to combine it with the recent graph based ANN techniques.
From Distillation to Hard Negative Sampling: Making Sparse Neural IR Models More Effective
Neural retrievers based on dense representations combined with Approximate Nearest Neighbors search have recently received a lot of attention, owing their success to distillation and/or better sampling of examples for training -- while still relying on the same backbone architecture.
An Efficiency Study for SPLADE Models
SPLADE efficiency can be controlled via a regularization factor, but solely controlling this regularization has been shown to not be efficient enough.
An Experimental Study on Pretraining Transformers from Scratch for IR
In this paper, we study the impact of the pretraining collection on the final IR effectiveness.
Naver Labs Europe (SPLADE) @ TREC Deep Learning 2022
This paper describes our participation to the 2022 TREC Deep Learning challenge.
Extending English IR methods to multi-lingual IR
This paper describes our participation in the 2023 WSDM CUP - MIRACL challenge.
Naver Labs Europe (SPLADE) @ TREC NeuCLIR 2022
This paper describes our participation in the 2022 TREC NeuCLIR challenge.
Parameter-Efficient Sparse Retrievers and Rerankers using Adapters
While previous studies have only experimented with dense retriever or in a cross lingual retrieval scenario, in this paper we aim to complete the picture on the use of adapters in IR.
Simple Yet Effective Neural Ranking and Reranking Baselines for Cross-Lingual Information Retrieval
The advent of multilingual language models has generated a resurgence of interest in cross-lingual information retrieval (CLIR), which is the task of searching documents in one language with queries from another.
AToMiC: An Image/Text Retrieval Test Collection to Support Multimedia Content Creation
This paper presents the AToMiC (Authoring Tools for Multimedia Content) dataset, designed to advance research in image/text cross-modal retrieval.
The tale of two MS MARCO -- and their unfair comparisons
This is why this paper aims to report the importance of this issue so that researchers can be made aware of this problem and appropriately report their results.
A Static Pruning Study on Sparse Neural Retrievers
Sparse neural retrievers, such as DeepImpact, uniCOIL and SPLADE, have been introduced recently as an efficient and effective way to perform retrieval with inverted indexes.
Benchmarking Middle-Trained Language Models for Neural Search
We compare both dense and sparse approaches under various finetuning protocols and middle training on different collections (MS MARCO, Wikipedia or Tripclick).
Resources for Brewing BEIR: Reproducible Reference Models and an Official Leaderboard
BEIR is a benchmark dataset for zero-shot evaluation of information retrieval models across 18 different domain/task combinations.
End-to-End Retrieval with Learned Dense and Sparse Representations Using Lucene
The bi-encoder architecture provides a framework for understanding machine-learned retrieval models based on dense and sparse vector representations.
SPLADE-v3: New baselines for SPLADE
A companion to the release of the latest version of the SPLADE library.
