Search Results for author:
Found 31 papers, 17 papers with code
DropletVideo: A Dataset and Approach to Explore Integral Spatio-Temporal Consistent Video Generation
Prior research, especially in open-source projects, primarily focuses on either temporal or spatial consistency, or their basic combination, such as appending a description of a camera movement after a prompt without constraining the outcomes of this movement.
Collaborative Filtering Meets Spectrum Shift: Connecting User-Item Interaction with Graph-Structured Side Information
However, when graph-structured side information (e. g., multimodal similarity graphs or social networks) is integrated into the U-I bipartite graph, existing graph collaborative filtering methods fall short of achieving satisfactory performance.
STAIR: Manipulating Collaborative and Multimodal Information for E-Commerce Recommendation
In order to combine the two distinct types of information, some additional challenges are encountered: 1) Modality erasure: Vanilla graph convolution, which proves rather useful in collaborative filtering, however erases multimodal information; 2) Modality forgetting: Multimodal information tends to be gradually forgotten as the recommendation loss essentially facilitates the learning of collaborative information.
CAdam: Confidence-Based Optimization for Online Learning
Modern recommendation systems frequently employ online learning to dynamically update their models with freshly collected data.
An Enhanced-State Reinforcement Learning Algorithm for Multi-Task Fusion in Large-Scale Recommender Systems
However, limited by their modeling pattern, all the current RL-MTF methods can only utilize user features as the state to generate actions for each user, but unable to make use of item features and other valuable features, which leads to suboptimal results.
Are LLM-based Recommenders Already the Best? Simple Scaled Cross-entropy Unleashes the Potential of Traditional Sequential Recommenders
Some studies have observed that LLMs, when fine-tuned by the cross-entropy (CE) loss with a full softmax, could achieve `state-of-the-art' performance in sequential recommendation.
Data Efficient Evaluation of Large Language Models and Text-to-Image Models via Adaptive Sampling
Empirical analysis across six NLP benchmarks reveals that: (1) quality-based sampling consistently achieves strong correlations (0. 85 to 0. 95) with full datasets at a 10\% sampling rate such as Quality SE and Quality CPD (2) clustering methods excel in specific benchmarks such as MMLU (3) no single method universally outperforms others across all metrics.
Comparing remote sensing-based forest biomass mapping approaches using new forest inventory plots in contrasting forests in northeastern and southwestern China
We then applied LightGBM and random forest regression to generate wall-to-wall AGB maps at 25 m resolution, using extensive GEDI footprints as well as Sentinel-1 data, ALOS-2 PALSAR-2 and Sentinel-2 optical data.
Enhancing User Interest based on Stream Clustering and Memory Networks in Large-Scale Recommender Systems
UIE enhances user interest including user profile and user history behavior sequences by leveraging the enhancement vectors and personalized enhancement vectors generated based on dynamic streaming clustering of similar users and items from multiple perspectives, which are stored and updated in memory networks.
Infer Induced Sentiment of Comment Response to Video: A New Task, Dataset and Baseline
In light of this, we introduces a novel research task, Multi-modal Sentiment Analysis for Comment Response of Video Induced(MSA-CRVI), aims to inferring opinions and emotions according to the comments response to micro video.
An Offline Reinforcement Learning Algorithm Customized for Multi-Task Fusion in Large-Scale Recommender Systems
IntegratedRL-MTF integrates offline RL model with our online exploration policy to relax overstrict and complicated constraints, which significantly improves its performance.
Pattern-wise Transparent Sequential Recommendation
It breaks the sequence of items into multi-level patterns that serve as atomic units throughout the recommendation process.
Understanding the Role of Cross-Entropy Loss in Fairly Evaluating Large Language Model-based Recommendation
Large language models (LLMs) have gained much attention in the recommendation community; some studies have observed that LLMs, fine-tuned by the cross-entropy loss with a full softmax, could achieve state-of-the-art performance already.
EEGPT: Pretrained Transformer for Universal and Reliable Representation of EEG Signals
However, challenges such as low signal-to-noise ratio (SNR), high inter-subject variability, and channel mismatch complicate the extraction of robust, universal EEG representations.
Inner-IoU: More Effective Intersection over Union Loss with Auxiliary Bounding Box
Based on the above, we first analyzed the BBR model and concluded that distinguishing different regression samples and using different scales of auxiliary bounding boxes to calculate losses can effectively accelerate the bounding box regression process.
Ranked #1 on
Object Detection
on PASCAL VOC 2007
(mAP@50 metric, using extra
training data)
Graph-enhanced Optimizers for Structure-aware Recommendation Embedding Evolution
Embedding plays a key role in modern recommender systems because they are virtual representations of real-world entities and the foundation for subsequent decision-making models.
X-TIME: An in-memory engine for accelerating machine learning on tabular data with CAMs
In this work, we focus on an overall analog-digital architecture implementing a novel increased precision analog CAM and a programmable network on chip allowing the inference of state-of-the-art tree-based ML models, such as XGBoost and CatBoost.
Less Emphasis on Difficult Layer Regions: Curriculum Learning for Singularly Perturbed Convection-Diffusion-Reaction Problems
Although Physics-Informed Neural Networks (PINNs) have been successfully applied in a wide variety of science and engineering fields, they can fail to accurately predict the underlying solution in slightly challenging convection-diffusion-reaction problems.
Sparse-based Domain Adaptation Network for OCTA Image Super-Resolution Reconstruction
To be more specific, we first perform a simple degradation of the 3x3 mm2/high-resolution (HR) image to obtain the synthetic LR image.
Understanding Adversarial Robustness from Feature Maps of Convolutional Layers
Our theoretical analysis discovers that larger convolutional feature maps before average pooling can contribute to better resistance to perturbations, but the conclusion is not true for max pooling.
Improve Deep Image Inpainting by Emphasizing the Complexity of Missing Regions
Deep image inpainting research mainly focuses on constructing various neural network architectures or imposing novel optimization objectives.
Graph-Based Stock Recommendation by Time-Aware Relational Attention Network
For a given group of stocks, the proposed TRAN model can output the ranking results of stocks according to their return ratios.
Missingness Augmentation: A General Approach for Improving Generative Imputation Models
However, data augmentation, as a simple yet effective method, has not received enough attention in this area.
An Orthogonal Classifier for Improving the Adversarial Robustness of Neural Networks
Neural networks are susceptible to artificially designed adversarial perturbations.
Ranked #1 on
Adversarial Attack
on CIFAR-10
Adversarial Momentum-Contrastive Pre-Training
Recently proposed adversarial self-supervised learning methods usually require big batches and long training epochs to extract robust features, which will bring heavy computational overhead on platforms with limited resources.
Revisiting Representation Degeneration Problem in Language Modeling
They call it the representation degeneration problem and propose a cosine regularization to solve it.
Improve Adversarial Robustness via Weight Penalization on Classification Layer
It is well-known that deep neural networks are vulnerable to adversarial attacks.
A Fast deflation Method for Sparse Principal Component Analysis via Subspace Projections
The implementation of conventional sparse principal component analysis (SPCA) on high-dimensional data sets has become a time consuming work.
SmoothOut: Smoothing Out Sharp Minima to Improve Generalization in Deep Learning
It becomes an open question whether escaping sharp minima can improve the generalization.
TernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learning
We mathematically prove the convergence of TernGrad under the assumption of a bound on gradients.
Coordinating Filters for Faster Deep Neural Networks
Moreover, Force Regularization better initializes the low-rank DNNs such that the fine-tuning can converge faster toward higher accuracy.
