Search Results for author:
Found 25 papers, 8 papers with code
Distributed Hierarchical GPU Parameter Server for Massive Scale Deep Learning Ads Systems
For example, a sponsored online advertising system can contain more than $10^{11}$ sparse features, making the neural network a massive model with around 10 TB parameters.
Fast ABC-Boost: A Unified Framework for Selecting the Base Class in Multi-Class Classification
Our framework has parameters $(s, g, w)$.
Package for Fast ABC-Boost
Although the gain formula in Li (2010) was derived for logistic regression loss, it is a generic formula for loss functions with second-derivatives.
pGMM Kernel Regression and Comparisons with Boosted Trees
In recent prior studies, the pGMM kernel has been extensively evaluated for classification tasks, for logistic regression, support vector machines, as well as deep neural networks.
F2GAN: Fusing-and-Filling GAN for Few-shot Image Generation
In this paper, we propose a Fusing-and-Filling Generative Adversarial Network (F2GAN) to generate realistic and diverse images for a new category with only a few images.
LIRA: Learnable, Imperceptible and Robust Backdoor Attacks
Under this optimization framework, the trigger generator function will learn to manipulate the input with imperceptible noise to preserve the model performance on the clean data and maximize the attack success rate on the poisoned data.
Machine Unlearning in Gradient Boosting Decision Trees
To the best of our knowledge, this is the first work that considers machine unlearning on GBDT.
Inductive Guided Filter: Real-time Deep Image Matting with Weakly Annotated Masks on Mobile Devices
A high efficient image matting method based on a weakly annotated mask is in demand for mobile applications.
Image Cropping with Composition and Saliency Aware Aesthetic Score Map
Aesthetic image cropping is a practical but challenging task which aims at finding the best crops with the highest aesthetic quality in an image.
Convergent Adaptive Gradient Methods in Decentralized Optimization
Specifically, we propose a general algorithmic framework that can convert existing adaptive gradient methods to their decentralized counterparts.
Thunder: a Fast Coordinate Selection Solver for Sparse Learning
L1 regularization has been broadly employed to pursue model sparsity.
On the Convergence of Decentralized Adaptive Gradient Methods
Adaptive gradient methods including Adam, AdaGrad, and their variants have been very successful for training deep learning models, such as neural networks.
Practical Adversarial Training with Differential Privacy for Deep Learning
In this work, we propose the practical adversarial training with differential privacy (DP-Adv), to combine the backbones from both communities and deliver robust and private models with high accuracy.
GCWSNet: Generalized Consistent Weighted Sampling for Scalable and Accurate Training of Neural Networks
For example, one can apply GCWS on the outputs of the last layer to boost the accuracy of trained deep neural networks.
Communication-Efficient TeraByte-Scale Model Training Framework for Online Advertising
In this paper, we propose a hardware-aware training workflow that couples the hardware topology into the algorithm design.
Proximity Graph Maintenance for Fast Online Nearest Neighbor Search
Given a vertex deletion request, we thoroughly investigate solutions to update the connections of the vertex.
FeatureBox: Feature Engineering on GPUs for Massive-Scale Ads Systems
In this paper, we propose FeatureBox, a novel end-to-end training framework that pipelines the feature extraction and the training on GPU servers to save the intermediate I/O of the feature extraction.
Constrained Approximate Similarity Search on Proximity Graph
Typically a three-stage mechanism is employed in those systems: (i) a small collection of items are first retrieved by (e. g.,) approximate near neighbor search algorithms; (ii) then a collection of constraints are applied on the retrieved items; (iii) a fine-grained ranking neural network is employed to determine the final recommendation.
Asymmetric Hashing for Fast Ranking via Neural Network Measures
Previous learning-to-hash approaches are also not suitable to solve the fast item ranking problem since they can take a significant amount of time and computation to train the hash functions.
Building K-Anonymous User Cohorts with\\ Consecutive Consistent Weighted Sampling (CCWS)
To retrieve personalized campaigns and creatives while protecting user privacy, digital advertising is shifting from member-based identity to cohort-based identity.
Practice with Graph-based ANN Algorithms on Sparse Data: Chi-square Two-tower model, HNSW, Sign Cauchy Projections
In this paper, we report our exploration of efficient search in sparse data with graph-based ANN algorithms (e. g., HNSW, or SONG which is the GPU version of HNSW), which are popular in industrial practice, e. g., search and ads (advertising).
Pb-Hash: Partitioned b-bit Hashing
In this study, we propose to re-use the hashes by partitioning the $B$ bits into $m$ chunks, e. g., $b\times m =B$.
Blockwise Feature Interaction in Recommendation Systems
Feature interactions can play a crucial role in recommendation systems as they capture complex relationships between user preferences and item characteristics.
DeepAuth: A DNN Authentication Framework by Model-Unique and Fragile Signature Embedding
After embedding, each model will respond distinctively to these key samples, which creates a model-unique signature as a strong tool for authentication and user identity.
GUITAR: Gradient Pruning toward Fast Neural Ranking
With the continuous popularity of deep learning and representation learning, fast vector search becomes a vital task in various ranking/retrieval based applications, say recommendation, ads ranking and question answering.
