Search Results for author:
Found 18 papers, 9 papers with code
A Framework for Controllable Multi-objective Learning with Annealed Stein Variational Hypernetworks
SVGD pushes a set of particles towards the Pareto set by applying a form of functional gradient descent, which helps to converge and diversify optimal solutions.
Provably Improving Generalization of Few-Shot Models with Synthetic Data
Few-shot image classification remains challenging due to the scarcity of labeled training examples.
Enhancing News Recommendation with Hierarchical LLM Prompting
Personalized news recommendation systems often struggle to effectively capture the complexity of user preferences, as they rely heavily on shallow representations, such as article titles and abstracts.
JEPA4Rec: Learning Effective Language Representations for Sequential Recommendation via Joint Embedding Predictive Architecture
Language representation learning has emerged as a promising approach for sequential recommendation, thanks to its ability to learn generalizable representations.
Improving Pareto Set Learning for Expensive Multi-objective Optimization via Stein Variational Hypernetworks
Through extensive experiments across both synthetic and real-world MOO benchmarks, we demonstrate that SVH-PSL significantly improves the quality of the learned Pareto set, offering a promising solution for expensive multi-objective optimization problems.
Keyword-driven Retrieval-Augmented Large Language Models for Cold-start User Recommendations
In this paper, we introduce KALM4Rec (Keyword-driven Retrieval-Augmented Large Language Models for Cold-start User Recommendations), a novel framework specifically designed to tackle this problem by requiring only a few input keywords from users in a practical scenario of cold-start user restaurant recommendations.
Improving Vietnamese-English Medical Machine Translation
Machine translation for Vietnamese-English in the medical domain is still an under-explored research area.
Towards Efficient Pareto-optimal Utility-Fairness between Groups in Repeated Rankings
On the Expohedron, we profile the Pareto curve which captures the trade-off between group fairness and user utility by identifying a finite number of Pareto optimal solutions.
A Curious Case of Searching for the Correlation between Training Data and Adversarial Robustness of Transformer Textual Models
First, empirical analyses show that (a) extracted features can be used with a lightweight classifier such as Random Forest to predict the attack success rate effectively, and (b) features with the most influence on the model robustness have a clear correlation with the robustness.
Zero-shot Object-Level OOD Detection with Context-Aware Inpainting
RONIN conditions the inpainting process with the predicted ID label, drawing the input object closer to the in-distribution domain.
Towards Efficient Communication and Secure Federated Recommendation System via Low-rank Training
Federated Recommendation (FedRec) systems have emerged as a solution to safeguard users' data in response to growing regulatory concerns.
Controllable Expensive Multi-objective Learning with Warm-starting Bayesian Optimization
Pareto Set Learning (PSL) is a promising approach for approximating the entire Pareto front in multi-objective optimization (MOO) problems.
Improving Heterogeneous Graph Learning with Weighted Mixed-Curvature Product Manifold
A promising candidate for the faithful embedding of data with varying structure is product manifolds of component spaces of different geometries (spherical, hyperbolic, or euclidean).
Improving Items and Contexts Understanding with Descriptive Graph for Conversational Recommendation
State-of-the-art methods on conversational recommender systems (CRS) leverage external knowledge to enhance both items' and contextual words' representations to achieve high quality recommendations and responses generation.
Improving Pareto Front Learning via Multi-Sample Hypernetworks
Pareto Front Learning (PFL) was recently introduced as an effective approach to obtain a mapping function from a given trade-off vector to a solution on the Pareto front, which solves the multi-objective optimization (MOO) problem.
Enhancing Few-shot Image Classification with Cosine Transformer
This might result in a significant difference between support and query samples, therefore undermining the performance of few-shot algorithms.
Improving Transformers with Probabilistic Attention Keys
Inspired by this observation, we propose Transformer with a Mixture of Gaussian Keys (Transformer-MGK), a novel transformer architecture that replaces redundant heads in transformers with a mixture of keys at each head.
VinDr-CXR: An open dataset of chest X-rays with radiologist's annotations
Most of the existing chest X-ray datasets include labels from a list of findings without specifying their locations on the radiographs.
