Qingming Huang

Unsupervised Open Domain Recognition by Semantic Discrepancy Minimization

2019

We address the unsupervised open domain recognition (UODR) problem, where categories in labeled source domain S is only a subset of those in unlabeled target domain T. The task is to correctly classify all samples …

Pareto Optimality for Fairness-constrained Collaborative Filtering

2021

The well-known collaborative filtering (CF) models typically optimize a single objective summed over all historical user-item interactions. Due to inevitable imbalances and biases in real-world data, they may develop a policy that unfairly discriminates against …

Geometry Interaction Knowledge Graph Embeddings

2022 · arXiv (Cornell University)

Knowledge graph (KG) embeddings have shown great power in learning representations of entities and relations for link prediction tasks. Previous work usually embeds KGs into a single geometric space such as Euclidean space (zero curved), …

Meta-Wrapper: Differentiable Wrapping Operator for User Interest Selection in CTR Prediction

2022 · arXiv (Cornell University)

Click-through rate (CTR) prediction, whose goal is to predict the probability of the user to click on an item, has become increasingly significant in the recommender systems. Recently, some deep learning models with the ability …

A Unified Perspective for Loss-Oriented Imbalanced Learning via Localization

2023 · arXiv (Cornell University)

Due to the inherent imbalance in real-world datasets, naïve Empirical Risk Minimization (ERM) tends to bias the learning process towards the majority classes, hindering generalization to minority classes. To rebalance the learning process, one straightforward …

Adaptive Feature Swapping for Unsupervised Domain Adaptation

2023

The bottleneck of visual domain adaptation always lies in the learning of domain invariant representations. In this paper, we present a simple but effective technique named Adaptive Feature Swapping for learning domain invariant features in …

Bundle Fragments into a Whole: Mining More Complete Clusters via Submodular Selection of Interesting webpages for Web Topic Detection

2024 · arXiv (Cornell University)

Organizing interesting webpages into hot topics is one of key steps to understand the trends of multimodal web data. A state-of-the-art solution is firstly to organize webpages into a large volume of multi-granularity topic candidates; …