Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- short-paperOctober 2024
EmbSum: Leveraging the Summarization Capabilities of Large Language Models for Content-Based Recommendations
- Chiyu Zhang,
- Yifei Sun,
- Minghao Wu,
- Jun Chen,
- Jie Lei,
- Muhammad Abdul-Mageed,
- Rong Jin,
- Angli Liu,
- Ji Zhu,
- Sem Park,
- Ning Yao,
- Bo Long
RecSys '24: Proceedings of the 18th ACM Conference on Recommender SystemsPages 1010–1015https://doi.org/10.1145/3640457.3688185Content-based recommendation systems play a crucial role in delivering personalized content to users in the digital world. In this work, we introduce EmbSum, a novel framework that enables offline pre-computations of users and candidate items while ...
- research-articleAugust 2024
FusionSF: Fuse Heterogeneous Modalities in a Vector Quantized Framework for Robust Solar Power Forecasting
KDD '24: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPages 5532–5543https://doi.org/10.1145/3637528.3671509Accurate solar power forecasting is crucial to integrate photovoltaic plants into the electric grid, schedule and secure the power grid safety. This problem becomes more demanding for those newly installed solar plants which lack sufficient operational ...
- research-articleMarch 2024
HyRSM++: Hybrid relation guided temporal set matching for few-shot action recognition
AbstractFew-shot action recognition is a challenging but practical problem aiming to learn a model that can be easily adapted to identify new action categories with only a few labeled samples. However, existing attempts still suffer from two drawbacks: (...
Highlights- A new temporal coherence regularization on videos is proposed.
- Capturing the intra- and inter-relations inside the episodic task.
- Reformulating the query-support metric as a set matching problem.
- research-articleMay 2024
OneNet: enhancing time series forecasting models under concept drift by online ensembling
NIPS '23: Proceedings of the 37th International Conference on Neural Information Processing SystemsArticle No.: 3066, Pages 69949–69980Online updating of time series forecasting models aims to address the concept drifting problem by efficiently updating forecasting models based on streaming data. Many algorithms are designed for online time series forecasting, with some exploiting cross-...
-
- research-articleMay 2024
One fits all: power general time series analysis by pretrained LM
NIPS '23: Proceedings of the 37th International Conference on Neural Information Processing SystemsArticle No.: 1877, Pages 43322–43355Although we have witnessed great success of pre-trained models in natural language processing (NLP) and computer vision (CV), limited progress has been made for general time series analysis. Unlike NLP and CV where a unified model can be used to perform ...
- research-articleOctober 2023
Self-Supervised Learning from Untrimmed Videos via Hierarchical Consistency
IEEE Transactions on Pattern Analysis and Machine Intelligence (ITPM), Volume 45, Issue 10Pages 12408–12426https://doi.org/10.1109/TPAMI.2023.3273415Natural untrimmed videos provide rich visual content for self-supervised learning. Yet most previous efforts to learn spatio-temporal representations rely on manually trimmed videos, such as Kinetics dataset (Carreira and Zisserman 2017), resulting in ...
- research-articleJuly 2023
AdaNPC: exploring non-parametric classifier for test-time adaptation
ICML'23: Proceedings of the 40th International Conference on Machine LearningArticle No.: 1748, Pages 41647–41676Many recent machine learning tasks focus to develop models that can generalize to unseen distributions. Domain generalization (DG) has become one of the key topics in various fields. Several literatures show that DG can be arbitrarily hard without ...
- research-articleJuly 2023
FeDXL: provable federated learning for deep X-risk optimization
ICML'23: Proceedings of the 40th International Conference on Machine LearningArticle No.: 479, Pages 11934–11966In this paper, we tackle a novel federated learning (FL) problem for optimizing a family of X-risks, to which no existing FL algorithms are applicable. In particular, the objective has the form of $\mathbb{E}_{\mathbf{z}\sim \mathcal{S}_1} f(\mathbb{E}_{\...
- research-articleApril 2023
Achieving Human Parity on Visual Question Answering
- Ming Yan,
- Haiyang Xu,
- Chenliang Li,
- Junfeng Tian,
- Bin Bi,
- Wei Wang,
- Xianzhe Xu,
- Ji Zhang,
- Songfang Huang,
- Fei Huang,
- Luo Si,
- Rong Jin
ACM Transactions on Information Systems (TOIS), Volume 41, Issue 3Article No.: 79, Pages 1–40https://doi.org/10.1145/3572833The Visual Question Answering (VQA) task utilizes both visual image and language analysis to answer a textual question with respect to an image. It has been a popular research topic with an increasing number of real-world applications in the last decade. ...
- research-articleMarch 2023
RETRACTED ARTICLE: Spatial-temporal deep learning model based rumor source identification in social networks
Journal of Combinatorial Optimization (SPJCO), Volume 45, Issue 3https://doi.org/10.1007/s10878-023-01018-5AbstractRumor source detection has long been an important but difficult problem. Due to the complexity of the underlying propagation model, most existing methods only rely on the limit observation of a single batch of single snapshot during the ...
- research-articleFebruary 2023
ParamCrop: Parametric Cubic Cropping for Video Contrastive Learning
IEEE Transactions on Multimedia (TOM), Volume 25Pages 9002–9014https://doi.org/10.1109/TMM.2023.3244126The central idea of contrastive learning is to discriminate between different instances and force different views from the same instance to share the same representation. To avoid trivial solutions, augmentation plays an important role in generating ...
- research-articleApril 2024
Stability and generalization analysis of gradient methods for shallow neural networks
NIPS '22: Proceedings of the 36th International Conference on Neural Information Processing SystemsArticle No.: 2794, Pages 38557–38570While significant theoretical progress has been achieved, unveiling the generalization mystery of overparameterized neural networks still remains largely elusive. In this paper, we study the generalization behavior of shallow neural networks (SNNs) by ...
- research-articleApril 2024
Improved fine-tuning by better leveraging pre-training data
NIPS '22: Proceedings of the 36th International Conference on Neural Information Processing SystemsArticle No.: 2360, Pages 32568–32581As a dominant paradigm, fine-tuning a pre-trained model on the target data is widely used in many deep learning applications, especially for small data sets. However, recent studies have empirically shown that training from scratch has the final ...
- research-articleApril 2024
Robust graph structure learning via multiple statistical tests
NIPS '22: Proceedings of the 36th International Conference on Neural Information Processing SystemsArticle No.: 2325, Pages 32083–32096Graph structure learning aims to learn connectivity in a graph from data. It is particularly important for many computer vision related tasks since no explicit graph structure is available for images for most cases. A natural way to construct a graph ...
- research-articleApril 2024
Grow and merge: a unified framework for continuous categories discovery
NIPS '22: Proceedings of the 36th International Conference on Neural Information Processing SystemsArticle No.: 1991, Pages 27455–27468Although a number of studies are devoted to novel category discovery, most of them assume a static setting where both labeled and unlabeled data are given at once for finding new categories. In this work, we focus on the application scenarios where ...
- research-articleApril 2024
FiLM: frequency improved legendre memory model for long-term time series forecasting
NIPS '22: Proceedings of the 36th International Conference on Neural Information Processing SystemsArticle No.: 921, Pages 12677–12690Recent studies have shown that deep learning models such as RNNs and Transformers have brought significant performance gains for long-term forecasting of time series because they effectively utilize historical information. We found, however, that there ...
- ArticleOctober 2022
KVT: k-NN Attention for Boosting Vision Transformers
AbstractConvolutional Neural Networks (CNNs) have dominated computer vision for years, due to its ability in capturing locality and translation invariance. Recently, many vision transformer architectures have been proposed and they show promising ...
- ArticleOctober 2022
TransFGU: A Top-Down Approach to Fine-Grained Unsupervised Semantic Segmentation
AbstractUnsupervised semantic segmentation aims to obtain high-level semantic representation on low-level visual features without manual annotations. Most existing methods are bottom-up approaches that try to group pixels into regions based on their ...