Search Results for author:
Found 41 papers, 20 papers with code
Enhancing Self-Attention with Knowledge-Assisted Attention Maps
Large-scale pre-trained language models have attracted extensive attentions in the research community and shown promising results on various tasks of natural language processing.
Align before Search: Aligning Ads Image to Text for Accurate Cross-Modal Sponsored Search
Conventional research mainly studies from the view of modeling the implicit correlations between images and texts for query-ads matching, ignoring the alignment of detailed product information and resulting in suboptimal search performance. In this work, we propose a simple alignment network for explicitly mapping fine-grained visual parts in ads images to the corresponding text, which leverages the co-occurrence structure consistency between vision and language spaces without requiring expensive labeled training data.
Ranked #1 on
Image-text matching
on CommercialAdsDataset
Model-enhanced Vector Index
We empirically show that our model achieves better performance on the commonly used academic benchmarks MSMARCO Passage and Natural Questions, with comparable serving latency to dense retrieval solutions.
Mitigating Semantic Confusion from Hostile Neighborhood for Graph Active Learning
Graph Active Learning (GAL), which aims to find the most informative nodes in graphs for annotation to maximize the Graph Neural Networks (GNNs) performance, has attracted many research efforts but remains non-trivial challenges.
Constraint-aware and Ranking-distilled Token Pruning for Efficient Transformer Inference
Deploying pre-trained transformer models like BERT on downstream tasks in resource-constrained scenarios is challenging due to their high inference cost, which grows rapidly with input sequence length.
To Copy Rather Than Memorize: A Vertical Learning Paradigm for Knowledge Graph Completion
Embedding models have shown great power in knowledge graph completion (KGC) task.
IRGen: Generative Modeling for Image Retrieval
While generative modeling has been ubiquitous in natural language processing and computer vision, its application to image retrieval remains unexplored.
UPRISE: Universal Prompt Retrieval for Improving Zero-Shot Evaluation
Large Language Models (LLMs) are popular for their impressive abilities, but the need for model-specific fine-tuning or task-specific prompt engineering can hinder their generalization.
SpaceEvo: Hardware-Friendly Search Space Design for Efficient INT8 Inference
The combination of Neural Architecture Search (NAS) and quantization has proven successful in automatically designing low-FLOPs INT8 quantized neural networks (QNN).
Estimating Treatment Effects from Irregular Time Series Observations with Hidden Confounders
Causal analysis for time series data, in particular estimating individualized treatment effect (ITE), is a key task in many real-world applications, such as finance, retail, healthcare, etc.
VL-Match: Enhancing Vision-Language Pretraining with Token-Level and Instance-Level Matching
Vision-Language Pretraining (VLP) has significantly improved the performance of various vision-language tasks with the matching of images and texts.
Label-Efficient Interactive Time-Series Anomaly Detection
Time-series anomaly detection is an important task and has been widely applied in the industry.
Convolution-enhanced Evolving Attention Networks
To the best of our knowledge, this is the first work that explicitly models the layer-wise evolution of attention maps.
SwiftPruner: Reinforced Evolutionary Pruning for Efficient Ad Relevance
Remarkably, under our latency requirement of 1900us on CPU, SwiftPruner achieves a 0. 86% higher AUC than the state-of-the-art uniform sparse baseline for BERT-Mini on a large scale real-world dataset.
Binary Classification with Positive Labeling Sources
Thus, in this work, we study the application of WS on binary classification tasks with positive labeling sources only.
A Neural Corpus Indexer for Document Retrieval
To this end, we propose Neural Corpus Indexer (NCI), a sequence-to-sequence network that generates relevant document identifiers directly for a designated query.
Stylized Knowledge-Grounded Dialogue Generation via Disentangled Template Rewriting
(2) How to cohere with context and preserve the knowledge when generating a stylized response.
Learning Multi-granularity User Intent Unit for Session-based Recommendation
Specifically, we creatively propose Multi-granularity Intent Heterogeneous Session Graph which captures the interactions between different granularity intent units and relieves the burden of long-dependency.
Multimodal Dialogue Response Generation
In such a low-resource setting, we devise a novel conversational agent, Divter, in order to isolate parameters that depend on multimodal dialogues from the entire generation model.
Creating Training Sets via Weak Indirect Supervision
Creating labeled training sets has become one of the major roadblocks in machine learning.
Graph Pointer Neural Networks
On the one hand, multi-hop-based approaches do not explicitly distinguish relevant nodes from a large number of multi-hop neighborhoods, leading to a severe over-smoothing problem.
WRENCH: A Comprehensive Benchmark for Weak Supervision
To address these problems, we introduce a benchmark platform, WRENCH, for thorough and standardized evaluation of WS approaches.
Attentive Knowledge-aware Graph Convolutional Networks with Collaborative Guidance for Personalized Recommendation
However, simply integrating KGs in current KG-based RS models is not necessarily a guarantee to improve the recommendation performance, which may even weaken the holistic model capability.
Click-Through Rate Prediction
Knowledge-Aware Recommendation
+1
Customizing Graph Neural Networks using Path Reweighting
Specifically, the proposed CustomGNN can automatically learn the high-level semantics for specific downstream tasks to highlight semantically relevant paths as well to filter out task-irrelevant noises in a graph.
TS2Vec: Towards Universal Representation of Time Series
Furthermore, to obtain the representation of an arbitrary sub-sequence in the time series, we can apply a simple aggregation over the representations of corresponding timestamps.
Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting
In this paper, we propose Spectral Temporal Graph Neural Network (StemGNN) to further improve the accuracy of multivariate time-series forecasting.
Syntax-BERT: Improving Pre-trained Transformers with Syntax Trees
Pre-trained language models like BERT achieve superior performances in various NLP tasks without explicit consideration of syntactic information.
Evolving Attention with Residual Convolutions
In this paper, we propose a novel and generic mechanism based on evolving attention to improve the performance of transformers.
Predictive Attention Transformer: Improving Transformer with Attention Map Prediction
Instead, we model their dependencies via a chain of prediction models that take previous attention maps as input to predict the attention maps of a new layer through convolutional neural networks.
AutoADR: Automatic Model Design for Ad Relevance
We add the model designed by AutoADR as a sub-model into the production Ad Relevance model.
CogTree: Cognition Tree Loss for Unbiased Scene Graph Generation
We first build a cognitive structure CogTree to organize the relationships based on the prediction of a biased SGG model.
Ranked #2 on
Scene Graph Generation
on Visual Genome
(mean Recall @20 metric)
Multivariate Time-series Anomaly Detection via Graph Attention Network
Anomaly detection on multivariate time-series is of great importance in both data mining research and industrial applications.
Cross-modal Knowledge Reasoning for Knowledge-based Visual Question Answering
Finally, we perform graph neural networks to infer the global-optimal answer by jointly considering all the concepts.
Automated Model Selection for Time-Series Anomaly Detection
The task is challenging because of the complex characteristics of time-series, which are messy, stochastic, and often without proper labels.
Mucko: Multi-Layer Cross-Modal Knowledge Reasoning for Fact-based Visual Question Answering
In this paper, we depict an image by a multi-modal heterogeneous graph, which contains multiple layers of information corresponding to the visual, semantic and factual features.
LadaBERT: Lightweight Adaptation of BERT through Hybrid Model Compression
BERT is a cutting-edge language representation model pre-trained by a large corpus, which achieves superior performances on various natural language understanding tasks.
Deeper Insights into Weight Sharing in Neural Architecture Search
With the success of deep neural networks, Neural Architecture Search (NAS) as a way of automatic model design has attracted wide attention.
TextNAS: A Neural Architecture Search Space tailored for Text Representation
Learning text representation is crucial for text classification and other language related tasks.
Customized Graph Embedding: Tailoring Embedding Vectors to different Applications
For these applications, graph embedding is crucial as it provides vector representations of the graph.
DeGNN: Characterizing and Improving Graph Neural Networks with Graph Decomposition
Despite the wide application of Graph Convolutional Network (GCN), one major limitation is that it does not benefit from the increasing depth and suffers from the oversmoothing problem.
Time-Series Anomaly Detection Service at Microsoft
At Microsoft, we develop a time-series anomaly detection service which helps customers to monitor the time-series continuously and alert for potential incidents on time.
