A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Geometric approach for unsupervised word embedding alignment.
A new method for unsupervised disentanglement using axis-aligned cliffs.
SrvfNet aligns multiple functional data to templates without supervision.
Paper proposes a novel method for aligning hierarchical data using optimal transport in hyperbolic spaces.
This paper studies aligning knowledge graphs from different sources or languages. Most existing methods train supervised methods for the alignment, which usually require a large number of aligned knowledge triplets. However, such a large number of aligned knowledge triplets may not be available or are expensive to obta…
A new method for aligning multiple distributions efficiently.
New method removes pseudo-label bias for unsupervised domain adaptation.
A new method for aligning datasets without known correspondences.
Proposes a regularization method for unsupervised domain adaptation that aligns predictions with target data's top singular vectors.
We propose a method for unsupervised domain adaptation that trains a shared embedding to align the joint distributions of inputs (domain) and outputs (classes), making any classifier agnostic to the domain. Joint alignment ensures that not only the marginal distributions of the domain are aligned, but the labels as wel…
Paper develops a new unsupervised scoring function for cross-lingual document alignment.
Proposes using Wasserstein barycenter for better multilingual alignment.
A new method for unsupervised domain adaptation using manifold learning.
Method generates intermediate domains to align source and target domains.
Unsupervised domain adaptation methods aim to alleviate performance degradation caused by domain-shift by learning domain-invariant representations. Existing deep domain adaptation methods focus on holistic feature alignment by matching source and target holistic feature distributions, without considering local feature…
SFAVEL distills features from language models for fact verification without annotations.
New method for robust distribution alignment using log-likelihood ratio and normalizing flows.
Unsupervised domain adaptation aims to transfer the classifier learned from the source domain to the target domain in an unsupervised manner. With the help of target pseudo-labels, aligning class-level distributions and learning the classifier in the target domain are two widely used objectives. Existing methods often …
Simple framework decouples word alignment and multilingual embedding mapping.
Recent unsupervised approaches to domain adaptation primarily focus on minimizing the gap between the source and the target domains through refining the feature generator, in order to learn a better alignment between the two domains. This minimization can be achieved via a domain classifier to detect target-domain feat…
In this paper, we propose a simple model referred as Contradistinguisher (CTDR) for unsupervised domain adaptation whose objective is to jointly learn to contradistinguish on unlabeled target domain in a fully unsupervised manner along with prior knowledge acquired by supervised learning on an entirely different domain…
We present a probabilistic model for unsupervised alignment of high-dimensional time-warped sequences based on the Dirichlet Process Mixture Model (DPMM). We follow the approach introduced in (Kazlauskaite, 2018) of simultaneously representing each data sequence as a composition of a true underlying function and a time…
Deep neural networks, trained with large amount of labeled data, can fail to generalize well when tested with examples from a \emph{target domain} whose distribution differs from the training data distribution, referred as the \emph{source domain}. It can be expensive or even infeasible to obtain required amount of lab…
MetFA aligns source and target domains for cross-device image classification.
Unsupervised domain adaptation aims to transfer and adapt knowledge learned from a labeled source domain to an unlabeled target domain. Key components of unsupervised domain adaptation include: (a) maximizing performance on the target, and (b) aligning the source and target domains. Traditionally, these tasks have eith…
Contradistinguisher learns to distinguish target domain without aligning source and target domains.
Prototype extraction framework for domain adaptation.
We solve a key problem in cross-lingual learning using a novel approach.
New method improves domain adaptation by aligning sub-domains.
We consider the task of aligning two sets of points in high dimension, which has many applications in natural language processing and computer vision. As an example, it was recently shown that it is possible to infer a bilingual lexicon, without supervised data, by aligning word embeddings trained on monolingual data. …
In this work, we connect two distinct concepts for unsupervised domain adaptation: feature distribution alignment between domains by utilizing the task-specific decision boundary and the Wasserstein metric. Our proposed sliced Wasserstein discrepancy (SWD) is designed to capture the natural notion of dissimilarity betw…
SHA improves fMRI alignment for cognitive state discovery.
Framework controls uncertainty in LLMs without labels or probabilities.
Joint alignment of a collection of functions is the process of independently transforming the functions so that they appear more similar to each other. Typically, such unsupervised alignment algorithms fail when presented with complex data sets arising from multiple modalities or make restrictive assumptions about the …
Geometric framework detects concept frustration between human concepts and machine representations.
Unsupervised machine translation---i.e., not assuming any cross-lingual supervision signal, whether a dictionary, translations, or comparable corpora---seems impossible, but nevertheless, Lample et al. (2018) recently proposed a fully unsupervised machine translation (MT) model. The model relies heavily on an adversari…
Geometric stability predicts steerability and detects drift in language models.
Can neural networks learn to compare graphs without feature engineering? In this paper, we show that it is possible to learn representations for graph similarity with neither domain knowledge nor supervision (i.e.\ feature engineering or labeled graphs). We propose Deep Divergence Graph Kernels, an unsupervised method …
Proposes a framework to improve domain adaptation without labeled data.
A new deep generative model captures global dependencies without supervision.
We present a model that can automatically learn alignments between high-dimensional data in an unsupervised manner. Our proposed method casts alignment learning in a framework where both alignment and data are modelled simultaneously. Further, we automatically infer groupings of different types of sequences within the …
We study the question of how to imitate tasks across domains with discrepancies such as embodiment, viewpoint, and dynamics mismatch. Many prior works require paired, aligned demonstrations and an additional RL step that requires environment interactions. However, paired, aligned demonstrations are seldom obtainable an…
Aligns attention distributions for improved accuracy and robustness.
MALI aligns distinct domains using labeled data.
Proposes novel losses for fine-grained categorical domain adaptation.
UDA improves ABI robustness but fails under certain prior misspecifications.
We address the problem of severe class imbalance in unsupervised domain adaptation, when the class spaces in source and target domains diverge considerably. Till recently, domain adaptation methods assumed the aligned class spaces, such that reducing distribution divergence makes the transfer between domains easier. Su…
Study improves GMM learning performance through multi-task and transfer learning.