Related papers: LAGO: Few-shot Crosslingual Embedding Inversion At…

With the advent of end-to-end deep learning approaches in machine translation, interest in word alignments initially decreased; however, they have again become a focus of research more recently. Alignments are useful for typological…

The advent of parameter-efficient fine-tuning methods has significantly reduced the computational burden of adapting large-scale pretrained models to diverse downstream tasks. However, existing approaches often struggle to achieve robust…

Large multilingual language models such as mBERT or XLM-R enable zero-shot cross-lingual transfer in various IR and NLP tasks. Cao et al. (2020) proposed a data- and compute-efficient method for cross-lingual adjustment of mBERT that uses a…

This article deals with the problem of distributed machine learning, in which agents update their models based on their local datasets, and aggregate the updated models collaboratively and in a fully decentralized manner. In this paper, we…

Although federated learning has increasingly gained attention in terms of effectively utilizing local devices for data privacy enhancement, recent studies show that publicly shared gradients in the training process can reveal the private…

We introduce a novel method for multilingual transfer that utilizes deep contextual embeddings, pretrained in an unsupervised fashion. While contextual embeddings have been shown to yield richer representations of meaning compared to their…

With the rapid growth of internet traffic, malicious network attacks have become increasingly frequent and sophisticated, posing significant threats to global cybersecurity. Traditional detection methods, including rule-based and machine…

Text-attributed graphs (TAGs) have emerged as a powerful representation for modeling complex relationships across diverse domains. With the rise of large language models (LLMs), there is growing interest in leveraging their capabilities for…

Regularization techniques are crucial to improving the generalization performance and training efficiency of deep neural networks. Many deep learning algorithms rely on weight decay, dropout, batch/layer normalization to converge faster and…

Recent advances in 3D Gaussian Splatting (3DGS) have enabled Simultaneous Localization and Mapping (SLAM) systems to build photorealistic maps. However, these maps lack the open-vocabulary semantic understanding required for advanced…

Few-shot transfer often shows substantial gain over zero-shot transfer~\cite{lauscher2020zero}, which is a practically useful trade-off between fully supervised and unsupervised learning approaches for multilingual pretrained model-based…

Learning from Text-Attributed Graphs (TAGs) has attracted significant attention due to its wide range of real-world applications. The rapid evolution of language models (LMs) has revolutionized the way we process textual data, which…

Named entity recognition on the in-domain supervised and few-shot settings have been extensively discussed in the NLP community and made significant progress. However, cross-domain NER, a more common task in practical scenarios, still poses…

Textual data is often represented as real-numbered embeddings in NLP, particularly with the popularity of large language models (LLMs) and Embeddings as a Service (EaaS). However, storing sensitive information as embeddings can be…

Graph Neural Networks (GNNs), specifically designed to process the graph data, have achieved remarkable success in various applications. Link stealing attacks on graph data pose a significant privacy threat, as attackers aim to extract…

Text-to-Image (T2I) models excel at synthesizing concepts such as nouns, appearances, and styles. To enable customized content creation based on a few example images of a concept, methods such as Textual Inversion and DreamBooth invert the…

Entity linking has recently been the subject of a significant body of research. Currently, the best performing approaches rely on trained mono-lingual models. Porting these approaches to other languages is consequently a difficult endeavor…

Most compilers for machine learning (ML) frameworks need to solve many correlated optimization problems to generate efficient machine code. Current ML compilers rely on heuristics based algorithms to solve these optimization problems one at…

The current state-of-the-art for few-shot cross-lingual transfer learning first trains on abundant labeled data in the source language and then fine-tunes with a few examples on the target language, termed target-adapting. Though this has…

Bilingual Lexical Induction (BLI) is a core challenge in NLP, it relies on the relative isomorphism of individual embedding spaces. Existing attempts aimed at controlling the relative isomorphism of different embedding spaces fail to…