Search Results for author:
Found 27 papers, 14 papers with code
Distributionally Robust Graph-based Recommendation System
DR-GNN addresses two core challenges: 1) To enable DRO to cater to graph data intertwined with GNN, we reinterpret GNN as a graph smoothing regularizer, thereby facilitating the nuanced application of DRO; 2) Given the typically sparse nature of recommendation data, which might impede robust optimization, we introduce slight perturbations in the training distribution to expand its support.
WildfireGPT: Tailored Large Language Model for Wildfire Analysis
The recent advancement of large language models (LLMs) represents a transformational capability at the frontier of artificial intelligence (AI) and machine learning (ML).
Knowledge Translation: A New Pathway for Model Compression
Deep learning has witnessed significant advancements in recent years at the cost of increasing training, inference, and model storage overhead.
CDR: Conservative Doubly Robust Learning for Debiased Recommendation
In recommendation systems (RS), user behavior data is observational rather than experimental, resulting in widespread bias in the data.
A data-driven approach to predict decision point choice during normal and evacuation wayfinding in multi-story buildings
This paper demonstrates the potential of applying a machine learning algorithm to study pedestrian route choice behavior in complex indoor buildings.
OpenGSL: A Comprehensive Benchmark for Graph Structure Learning
Moreover, we observe that the learned graph structure demonstrates a strong generalization ability across different GNN models, despite the high computational and space consumption.
Generalizable Black-Box Adversarial Attack with Meta Learning
In the scenario of black-box adversarial attack, the target model's parameters are unknown, and the attacker aims to find a successful adversarial perturbation based on query feedback under a query budget.
Robust Sequence Networked Submodular Maximization
The approximation ratio of the algorithm depends both on the number of the removed elements and the network topology.
Statistical treatment of convolutional neural network super-resolution of inland surface wind for subgrid-scale variability quantification
For each downscaling factor, we consider three CNN configurations that generate super-resolved predictions of fine-scale wind speed, which take between 1 to 3 input fields: coarse wind speed, fine-scale topography, and diurnal cycle.
Accelerating Diffusion Sampling with Classifier-based Feature Distillation
Instead of aligning output images, we distill teacher's sharpened feature distribution into the student with a dataset-independent classifier, making the student focus on those important features to improve performance.
Multi-Scale Architectures Matter: On the Adversarial Robustness of Flow-based Lossless Compression
As a probabilistic modeling technique, the flow-based model has demonstrated remarkable potential in the field of lossless compression \cite{idf, idf++, lbb, ivpf, iflow},.
sqSGD: Locally Private and Communication Efficient Federated Learning
In addition, with fixed privacy and communication level, the performance of sqSGD significantly dominates that of various baseline algorithms.
Improving Knowledge Graph Embedding via Iterative Self-Semantic Knowledge Distillation
Iteratively incorporating and accumulating iteration-based semantic information enables the low-dimensional model to be more expressive for better link prediction in KGs.
Knowledge Distillation with the Reused Teacher Classifier
Knowledge distillation aims to compress a powerful yet cumbersome teacher model into a lightweight student model without much sacrifice of performance.
Ranked #3 on
Knowledge Distillation
on CIFAR-100
Online Adversarial Distillation for Graph Neural Networks
However, its effect on graph neural networks is less than satisfactory since the graph topology and node attributes are likely to change in a dynamic way and in this case a static teacher model is insufficient in guiding student training.
Spectral Variability Augmented Sparse Unmixing of Hyperspectral Images
Spectral unmixing (SU) expresses the mixed pixels existed in hyperspectral images as the product of endmember and abundance, which has been widely used in hyperspectral imagery analysis.
Exploring the Connection between Knowledge Distillation and Logits Matching
Knowledge distillation is a generalized logits matching technique for model compression.
Practical Locally Private Federated Learning with Communication Efficiency
We also initialize a discussion about the role of quantization and perturbation in FL algorithm design with privacy and communication constraints.
Cross-Layer Distillation with Semantic Calibration
Knowledge distillation is a technique to enhance the generalization ability of a student model by exploiting outputs from a teacher model.
SamWalker++: recommendation with informative sampling strategy
However, the social network information may not be available in many recommender systems, which hinders application of SamWalker.
CoSam: An Efficient Collaborative Adaptive Sampler for Recommendation
To deal with these problems, we propose an efficient and effective collaborative sampling method CoSam, which consists of: (1) a collaborative sampler model that explicitly leverages user-item interaction information in sampling probability and exhibits good properties of normalization, adaption, interaction information awareness, and sampling efficiency; and (2) an integrated sampler-recommender framework, leveraging the sampler model in prediction to offset the bias caused by uneven sampling.
Boosting Black-Box Attack with Partially Transferred Conditional Adversarial Distribution
This work studies black-box adversarial attacks against deep neural networks (DNNs), where the attacker can only access the query feedback returned by the attacked DNN model, while other information such as model parameters or the training datasets are unknown.
Toward Adversarial Robustness via Semi-supervised Robust Training
In this work, we propose a novel defense method, the robust training (RT), by jointly minimizing two separated risks ($R_{stand}$ and $R_{rob}$), which is with respect to the benign example and its neighborhoods respectively.
Fast Adaptively Weighted Matrix Factorization for Recommendation with Implicit Feedback
A popular and effective approach for implicit recommendation is to treat unobserved data as negative but downweight their confidence.
Adversarial Attack on Deep Product Quantization Network for Image Retrieval
Deep product quantization network (DPQN) has recently received much attention in fast image retrieval tasks due to its efficiency of encoding high-dimensional visual features especially when dealing with large-scale datasets.
An Accuracy-Lossless Perturbation Method for Defending Privacy Attacks in Federated Learning
However, the strong defence ability and high learning accuracy of these schemes cannot be ensured at the same time, which will impede the wide application of FL in practice (especially for medical or financial institutions that require both high accuracy and strong privacy guarantee).
Online Knowledge Distillation with Diverse Peers
The second-level distillation is performed to transfer the knowledge in the ensemble of auxiliary peers further to the group leader, i. e., the model used for inference.
