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.
A new framework pretrains a single GNN model for diverse graphs, overcoming domain-specific challenges.
Unified framework for transfer learning regression without extra cost.
Cross-domain collaborative filtering (CF) aims to alleviate data sparsity in single-domain CF by leveraging knowledge transferred from related domains. Many traditional methods focus on enriching compared neighborhood relations in CF directly to address the sparsity problem. In this paper, we propose superhighway const…
Sparse coding has shown its power as an effective data representation method. However, up to now, all the sparse coding approaches are limited within the single domain learning problem. In this paper, we extend the sparse coding to cross domain learning problem, which tries to learn from a source domain to a target dom…
Cross-domain recommendation has been proposed to transfer user behavior pattern by pooling together the rating data from multiple domains to alleviate the sparsity problem appearing in single rating domains. However, previous models only assume that multiple domains share a latent common rating pattern based on the use…
ADGAN improves risk tolerance prediction by aligning cross-domain data.
With the proliferation of social media platforms and e-commerce sites, several cross-domain collaborative filtering strategies have been recently introduced to transfer the knowledge of user preferences across domains. The main challenge of cross-domain recommendation is to weigh and learn users' different behaviors in…
Nowadays, users open multiple accounts on social media platforms and e-commerce sites, expressing their personal preferences on different domains. However, users' behaviors change across domains, depending on the content that users interact with, such as movies, music, clothing and retail products. In this paper, we pr…
GWIL uses Gromov-Wasserstein distance to align expert and imitation agent states.
Cross-domain recommendation can alleviate the data sparsity problem in recommender systems. To transfer the knowledge from one domain to another, one can either utilize the neighborhood information or learn a direct mapping function. However, all existing methods ignore the high-order connectivity information in cross-…
This paper improves cross-domain learning using random forests for manifold alignment.
CosML combines domain-specific meta-learners for cross-domain few-shot classification.
Ensuring the security of transactions is currently one of the major challenges that banking systems deal with. The usage of face for biometric authentication of users is attracting large investments from banks worldwide due to its convenience and acceptability by people, especially in cross-domain scenarios, in which f…
Dual-structured method improves cross-domain imitation learning.
New approach improves cross-domain recommendation for sparse target domains.
Novel methods robustify Gromov-Wasserstein distance for cross-domain alignment.
A new model for imputing missing values in time series data across domains.
Meta learning enables cross-domain Hamiltonian dynamics.
Cross-domain recommendation has long been one of the major topics in recommender systems. Recently, various deep models have been proposed to transfer the learned knowledge across domains, but most of them focus on extracting abstract transferable features from auxilliary contents, e.g., images and review texts, and th…
Cross-domain sentiment analysis is currently a hot topic in the research and engineering areas. One of the most popular frameworks in this field is the domain-invariant representation learning (DIRL) paradigm, which aims to learn a distribution-invariant feature representation across domains. However, in this work, we …
Paper proposes LMM-PQS for cross-domain few-shot learning.
The cross-domain recommendation technique is an effective way of alleviating the data sparse issue in recommender systems by leveraging the knowledge from relevant domains. Transfer learning is a class of algorithms underlying these techniques. In this paper, we propose a novel transfer learning approach for cross-doma…
We tackle unsupervised anomaly detection (UAD), a problem of detecting data that significantly differ from normal data. UAD is typically solved by using density estimation. Recently, deep neural network (DNN)-based density estimators, such as Normalizing Flows, have been attracting attention. However, one of their draw…
The recent empirical success of unsupervised cross-domain mapping algorithms, between two domains that share common characteristics, is not well-supported by theoretical justifications. This lacuna is especially troubling, given the clear ambiguity in such mappings. We work with adversarial training methods based on IP…
Cross-Domain Collaborative Filtering (CDCF) provides a way to alleviate data sparsity and cold-start problems present in recommendation systems by exploiting the knowledge from related domains. Existing CDCF models are either based on matrix factorization or deep neural networks. Either of the techniques in isolation m…
Learning effective embedding has been proved to be useful in many real-world problems, such as recommender systems, search ranking and online advertisement. However, one of the challenges is data sparsity in learning large-scale item embedding, as users' historical behavior data are usually lacking or insufficient in a…
Cross-domain sentiment classification (CDSC) is an importance task in domain adaptation and sentiment classification. Due to the domain discrepancy, a sentiment classifier trained on source domain data may not works well on target domain data. In recent years, many researchers have used deep neural network models for c…
Clustering consists of grouping together samples giving their similar properties. The problem of modeling simultaneously groups of samples and features is known as Co-Clustering. This paper introduces ROCCO - a Robust Continuous Co-Clustering algorithm. ROCCO is a scalable, hyperparameter-free, easy and ready to use al…
Proposes a new method for manifold alignment using geometry-regularized twin autoencoders.
Task-agnostic data augmentation shows little benefit for pretrained transformers.
Automated anomaly detection is essential for managing information and communications technology (ICT) systems to maintain reliable services with minimum burden on operators. For detecting varying and continually emerging anomalies as differences from normal states, learning normal relationships inherent among cross-dom…
Cross-domain visual data matching is one of the fundamental problems in many real-world vision tasks, e.g., matching persons across ID photos and surveillance videos. Conventional approaches to this problem usually involves two steps: i) projecting samples from different domains into a common space, and ii) computing (…
Analyzes stock trends and e-commerce user behavior using Twitter data.
Pretraining models improves text classification accuracy, but diminishing returns are observed with large datasets.
New framework selects high-quality pretraining data without training LLMs.
Paper studies how few pretraining tasks are needed for a linear model to solve new tasks.
Fine-grained pretraining improves neural network's ability to learn rare features.
Method constructs finance LLMs without instruction data using pretraining and model merging.
Mask-reconstruction pretraining helps in downstream tasks by capturing more semantic features.
A new slicing method reduces computational cost for cross-domain alignment.
Paper introduces a multi-stage influence function to track model predictions.
This large scale study focuses on quantifying what X-rays diagnostic prediction tasks generalize well across multiple different datasets. We present evidence that the issue of generalization is not due to a shift in the images but instead a shift in the labels. We study the cross-domain performance, agreement between m…
Pretraining method enhances dialogue representation learning across various tasks.
Synthetic continued pretraining enhances model performance with synthetic data.
WeatherFormer learns robust weather features from small datasets.
New findings on representation changes in transfer learning.
Theoretical analysis of data quality and synergies in LLMs.
Denoised smoothing defends pretrained classifiers against adversarial attacks.