Search Results for author:
Found 34 papers, 16 papers with code
Matching-oriented Embedding Quantization For Ad-hoc Retrieval
In this work, we propose the Matching-oriented Product Quantization (MoPQ), where a novel objective Multinoulli Contrastive Loss (MCL) is formulated.
Self-Supervised Text Erasing with Controllable Image Synthesis
The synthetic training images with erasure ground-truth are then fed to train a coarse-to-fine erasing network.
BSAL: A Framework of Bi-component Structure and Attribute Learning for Link Prediction
Regarding missing link inference of diverse networks, we revisit the link prediction techniques and identify the importance of both the structural and attribute information.
HRCF: Enhancing Collaborative Filtering via Hyperbolic Geometric Regularization
Through theoretical analysis, we further show that our proposal is able to tackle the over-smoothing problem caused by hyperbolic aggregation and also brings the models a better discriminative ability.
Distill-VQ: Learning Retrieval Oriented Vector Quantization By Distilling Knowledge from Dense Embeddings
We perform comprehensive explorations for the optimal conduct of knowledge distillation, which may provide useful insights for the learning of VQ based ANN index.
Visualizing the Relationship Between Encoded Linguistic Information and Task Performance
To this end, we study the dynamic relationship between the encoded linguistic information and task performance from the viewpoint of Pareto Optimality.
Investigating Data Variance in Evaluations of Automatic Machine Translation Metrics
Current practices in metric evaluation focus on one single dataset, e. g., Newstest dataset in each year's WMT Metrics Shared Task.
A Mutually Reinforced Framework for Pretrained Sentence Embeddings
Instead of relying on annotation heuristics defined by humans, it leverages the sentence representation model itself and realizes the following iterative self-supervision process: on one hand, the improvement of sentence representation may contribute to the quality of data annotation; on the other hand, more effective data annotation helps to generate high-quality positive samples, which will further improve the current sentence representation model.
Reinforcement Routing on Proximity Graph for Efficient Recommendation
Instead of searching the nearest neighbor for the query, we search the item with maximum inner product with query on the proximity graph.
Progressively Optimized Bi-Granular Document Representation for Scalable Embedding Based Retrieval
In this work, we tackle this problem with Bi-Granular Document Representation, where the lightweight sparse embeddings are indexed and standby in memory for coarse-grained candidate search, and the heavyweight dense embeddings are hosted in disk for fine-grained post verification.
Meta-learning with an Adaptive Task Scheduler
In ATS, for the first time, we design a neural scheduler to decide which meta-training tasks to use next by predicting the probability being sampled for each candidate task, and train the scheduler to optimize the generalization capacity of the meta-model to unseen tasks.
Learned Index with Dynamic $\epsilon$
We theoretically analyze prediction error bounds that link $\epsilon$ with data characteristics for an illustrative learned index method.
Fast Variational AutoEncoder with Inverted Multi-Index for Collaborative Filtering
Variational AutoEncoder (VAE) has been extended as a representative nonlinear method for collaborative filtering.
Linear-Time Self Attention with Codeword Histogram for Efficient Recommendation
Inspired by the idea of vector quantization that uses cluster centroids to approximate items, we propose LISA (LInear-time Self Attention), which enjoys both the effectiveness of vanilla self-attention and the efficiency of sparse attention.
Rethinking Lifelong Sequential Recommendation with Incremental Multi-Interest Attention
With the rapid development of these services in the last two decades, users have accumulated a massive amount of behavior data.
Assessing Dialogue Systems with Distribution Distances
An important aspect of developing dialogue systems is how to evaluate and compare the performance of different systems.
GraphFormers: GNN-nested Transformers for Representation Learning on Textual Graph
The representation learning on textual graph is to generate low-dimensional embeddings for the nodes based on the individual textual features and the neighbourhood information.
A Unified Transferable Model for ML-Enhanced DBMS
We propose to explore the transferabilities of the ML methods both across tasks and across DBs to tackle these fundamental drawbacks.
Hybrid Encoder: Towards Efficient and Precise Native AdsRecommendation via Hybrid Transformer Encoding Networks
For the sake of efficient recommendation, conventional methods would generate user and advertisement embeddings independently with a siamese transformer encoder, such that approximate nearest neighbour search (ANN) can be leveraged.
Matching-oriented Product Quantization For Ad-hoc Retrieval
In this work, we propose the Matching-oriented Product Quantization (MoPQ), where a novel objective Multinoulli Contrastive Loss (MCL) is formulated.
Efficient Optimal Selection for Composited Advertising Creatives with Tree Structure
Based on the tree structure, Thompson sampling is adapted with dynamic programming, leading to efficient exploration for potential ad creatives with the largest CTR.
Automated Creative Optimization for E-Commerce Advertising
However, interactions between creative elements may be more complex than the inner product, and the FM-estimated CTR may be of high variance due to limited feedback.
A Hybrid Bandit Model with Visual Priors for Creative Ranking in Display Advertising
Creative plays a great important role in e-commerce for exhibiting products.
Sampling-Decomposable Generative Adversarial Recommender
The GAN-style recommenders (i. e., IRGAN) addresses the challenge by learning a generator and a discriminator adversarially, such that the generator produces increasingly difficult samples for the discriminator to accelerate optimizing the discrimination objective.
Deep Pairwise Hashing for Cold-start Recommendation
Specifically, we first pre-train robust item representation from item content data by a Denoising Auto-encoder instead of other deterministic deep learning frameworks; then we finetune the entire framework by adding a pairwise loss objective with discrete constraints; moreover, DPH aims to minimize a pairwise ranking loss that is consistent with the ultimate goal of recommendation.
Learning to Transfer Graph Embeddings for Inductive Graph based Recommendation
The transfer network is designed to approximate the learned item embeddings from graph neural networks by taking each item's visual content as input, in order to tackle the new segment problem in the test phase.
GoGNN: Graph of Graphs Neural Network for Predicting Structured Entity Interactions
We observe that existing works on structured entity interaction prediction cannot properly exploit the unique graph of graphs model.
Lightrec: A memory and search-efficient recommender system
On top of such a structure, LightRec will have an item represented as additive composition of B codewords, which are optimally selected from each of the codebooks.
Binarized Graph Neural Network
Our proposed method can be seamlessly integrated into the existing GNN-based embedding approaches to binarize the model parameters and learn the compact embedding.
A Novel User Representation Paradigm for Making Personalized Candidate Retrieval
Our work is undergoing a anonymous review, and it will soon be released after the notification.
Binarized Collaborative Filtering with Distilling Graph Convolutional Networks
Then we distill the ranking information derived from GCN into binarized collaborative filtering, which makes use of binary representation to improve the efficiency of online recommendation.
MCNE: An End-to-End Framework for Learning Multiple Conditional Network Representations of Social Network
Recently, the Network Representation Learning (NRL) techniques, which represent graph structure via low-dimension vectors to support social-oriented application, have attracted wide attention.
A Survey on Session-based Recommender Systems
In recent years, session-based recommender systems (SBRSs) have emerged as a new paradigm of RSs.
Binarized Attributed Network Embedding
To this end, we present a Binarized Attributed Network Embedding model (BANE for short) to learn binary node representation.
Ranked #1 on
Link Prediction
on Wiki
