Search Results for author:
Found 33 papers, 8 papers with code
Latent Neural Operator Pretraining for Solving Time-Dependent PDEs
We achieve universal transformation through pretraining on hybrid time-dependent PDE dataset to extract representations of different physical systems and solve various time-dependent PDEs in the latent space through finetuning on single PDE dataset.
Latent Neural Operator for Solving Forward and Inverse PDE Problems
In particular, we first propose Physics-Cross-Attention (PhCA) transforming representation from the geometric space to the latent space, then learn the operator in the latent space, and finally recover the real-world geometric space via the inverse PhCA map.
Fed-Credit: Robust Federated Learning with Credibility Management
Aiming at privacy preservation, Federated Learning (FL) is an emerging machine learning approach enabling model training on decentralized devices or data sources.
Effective Gradient Sample Size via Variation Estimation for Accelerating Sharpness aware Minimization
Concretely, we discover that the gradient of SAM is a combination of the gradient of SGD and the Projection of the Second-order gradient matrix onto the First-order gradient (PSF).
Adversarial Bandits with Multi-User Delayed Feedback: Theory and Application
Thus, we formulate an adversarial MAB problem with multi-user delayed feedback and design a modified EXP3 algorithm MUD-EXP3, which makes a decision at each round by considering the importance-weighted estimator of the received feedback from different users.
A Fast Task Offloading Optimization Framework for IRS-Assisted Multi-Access Edge Computing System
Terahertz communication networks and intelligent reflecting surfaces exhibit significant potential in advancing wireless networks, particularly within the domain of aerial-based multi-access edge computing systems.
DCP-NAS: Discrepant Child-Parent Neural Architecture Search for 1-bit CNNs
One natural approach is to use 1-bit CNNs to reduce the computation and memory cost of NAS by taking advantage of the strengths of each in a unified framework, while searching the 1-bit CNNs is more challenging due to the more complicated processes involved.
Few-Shot Learning with Visual Distribution Calibration and Cross-Modal Distribution Alignment
However, with only a few training images, there exist two crucial problems: (1) the visual feature distributions are easily distracted by class-irrelevant information in images, and (2) the alignment between the visual and language feature distributions is difficult.
Configurable Spatial-Temporal Hierarchical Analysis for Flexible Video Anomaly Detection
Since the anomaly set is complicated and unbounded, our STHA can adjust its detection ability to adapt to the human detection demands and the complexity degree of anomaly that happened in the history of a scene.
GPT4Rec: A Generative Framework for Personalized Recommendation and User Interests Interpretation
The generated queries naturally serve as interpretable representations of user interests and can be searched to recommend cold-start items.
A Semi-supervised Sensing Rate Learning based CMAB Scheme to Combat COVID-19 by Trustful Data Collection in the Crowd
In this paper, an incentive mechanism named Semi-supervision based Combinatorial Multi-Armed Bandit reverse Auction (SCMABA) is proposed to solve the recruitment problem of multiple unknown and strategic workers in MCS.
Rethinking the Number of Shots in Robust Model-Agnostic Meta-Learning
Based on this observation, we propose a simple strategy, i. e., increasing the number of training shots, to mitigate the loss of intrinsic dimension caused by robustness-promoting regularization.
CAIBC: Capturing All-round Information Beyond Color for Text-based Person Retrieval
Indeed, color information is an important decision-making accordance for retrieval, but the over-reliance on color would distract the model from other key clues (e. g. texture information, structural information, etc.
Look Before You Leap: Improving Text-based Person Retrieval by Learning A Consistent Cross-modal Common Manifold
We evaluate our proposed method on two text-based person retrieval datasets CUHK-PEDES and RSTPReid.
Contrastive Learning for Interactive Recommendation in Fashion
Recommender systems and search are both indispensable in facilitating personalization and ease of browsing in online fashion platforms.
Bi-level Doubly Variational Learning for Energy-based Latent Variable Models
In this paper, we propose Bi-level doubly variational learning (BiDVL), which is based on a new bi-level optimization framework and two tractable variational distributions to facilitate learning EBLVMs.
Delving into the Estimation Shift of Batch Normalization in a Network
We define the estimation shift magnitude of BN to quantitatively measure the difference between its estimated population statistics and expected ones.
DSSL: Deep Surroundings-person Separation Learning for Text-based Person Retrieval
Many previous methods on text-based person retrieval tasks are devoted to learning a latent common space mapping, with the purpose of extracting modality-invariant features from both visual and textual modality.
Ranked #8 on
Text based Person Retrieval
on RSTPReid
Personalized Embedding-based e-Commerce Recommendations at eBay
Recommender systems are an essential component of e-commerce marketplaces, helping consumers navigate massive amounts of inventory and find what they need or love.
IDARTS: Interactive Differentiable Architecture Search
Differentiable Architecture Search (DARTS) improves the efficiency of architecture search by learning the architecture and network parameters end-to-end.
Item-based Collaborative Filtering with BERT
In e-commerce, recommender systems have become an indispensable part of helping users explore the available inventory.
Mimic and Rephrase: Reflective Listening in Open-Ended Dialogue
Reflective listening{--}demonstrating that you have heard your conversational partner{--}is key to effective communication.
Multi-Kernel Capsule Network for Schizophrenia Identification
Methods: To overcome the aforementioned drawbacks, we proposed a multi-kernel capsule network (MKCapsnet), which was developed by considering the brain anatomical structure.
Accelerating temporal action proposal generation via high performance computing
It is found that, compared to the traditional Parameter Server architecture, our parallel architecture has higher efficiency on temporal action detection task with multiple GPUs, which is suitable for dealing with the tasks of temporal action proposal generation, especially for large datasets of millions of videos.
AED-Net: An Abnormal Event Detection Network
It is challenging to detect the anomaly in crowded scenes for quite a long time.
Region based Ensemble Learning Network for Fine-grained Classification
Our approach contains a detection module and a module for classification.
Generative Neural Networks for Anomaly Detection in Crowded Scenes
Security surveillance is critical to social harmony and people's peaceful life.
Ranked #3 on
Abnormal Event Detection In Video
on UBI-Fights
Attention-based Mixture Density Recurrent Networks for History-based Recommendation
The goal of personalized history-based recommendation is to automatically output a distribution over all the items given a sequence of previous purchases of a user.
SAM: Semantic Attribute Modulation for Language Modeling and Style Variation
This paper presents a Semantic Attribute Modulation (SAM) for language modeling and style variation.
adaptive direction information in differential evolution for numerical optimization
In most of the DE algorithms, the neighborhood and direction information are not fully and simultaneously exploited to guide the search.
Automatic Instrument Recognition in Polyphonic Music Using Convolutional Neural Networks
Traditional methods to tackle many music information retrieval tasks typically follow a two-step architecture: feature engineering followed by a simple learning algorithm.
Larger-Context Language Modelling
In the experi- ments, we evaluate the proposed approach while varying the number of context sentences and observe that the proposed late fusion is superior to the usual way of incorporating additional inputs to the LSTM.
