Search Results for author:
Found 35 papers, 11 papers with code
Retrofitting Temporal Graph Neural Networks with Transformer
We also adapt Transformer codebase to train TF-TGN efficiently with multiple GPUs.
An Empirical Examination of Balancing Strategy for Counterfactual Estimation on Time Series
Counterfactual estimation from observations represents a critical endeavor in numerous application fields, such as healthcare and finance, with the primary challenge being the mitigation of treatment bias.
Who is Authentic Speaker
Therefore our experiments are geared towards recognising the source speakers given the converted voices, which are generated by using FragmentVC on the randomly paired utterances from source and target speakers.
Towards Controllable Time Series Generation
This underscores its adeptness in seamlessly integrating latent features with external conditions.
Diversity-Aware $k$-Maximum Inner Product Search Revisited
To bridge this gap, we revisit and refine the diversity-aware $k$MIPS (D$k$MIPS) problem by incorporating two well-known diversity objectives -- minimizing the average and maximum pairwise item similarities within the results -- into the original relevance objective.
From Zero to Hero: Detecting Leaked Data through Synthetic Data Injection and Model Querying
In this paper, we concentrate on the domain of tabular data and introduce a novel methodology, Local Distribution Shifting Synthesis (\textsc{LDSS}), to detect leaked data that are used to train classification models.
TSGBench: Time Series Generation Benchmark
Synthetic Time Series Generation (TSG) is crucial in a range of applications, including data augmentation, anomaly detection, and privacy preservation.
BenchTemp: A General Benchmark for Evaluating Temporal Graph Neural Networks
To handle graphs in which features or connectivities are evolving over time, a series of temporal graph neural networks (TGNNs) have been proposed.
Does Misclassifying Non-confounding Covariates as Confounders Affect the Causal Inference within the Potential Outcomes Framework?
Most causal inference models based on the POF (CIMs-POF) are designed for eliminating confounding bias and default to an underlying assumption of Confounding Covariates.
VLUCI: Variational Learning of Unobserved Confounders for Counterfactual Inference
By disentangling observed and unobserved confounders, VLUCI constructs a doubly variational inference model to approximate the distribution of unobserved confounders, which are used for inferring more accurate counterfactual outcomes.
De-confounding Representation Learning for Counterfactual Inference on Continuous Treatment via Generative Adversarial Network
Extensive experiments on synthetic datasets show that the DRL model performs superiorly in learning de-confounding representations and outperforms state-of-the-art counterfactual inference models for continuous treatment variables.
Lightweight-Yet-Efficient: Revitalizing Ball-Tree for Point-to-Hyperplane Nearest Neighbor Search
Finding the nearest neighbor to a hyperplane (or Point-to-Hyperplane Nearest Neighbor Search, simply P2HNNS) is a new and challenging problem with applications in many research domains.
Simple, Effective and General: A New Backbone for Cross-view Image Geo-localization
To address the above three challenges for cross-view image matching, we propose a new backbone network, named Simple Attention-based Image Geo-localization network (SAIG).
Ranked #2 on
Image-Based Localization
on VIGOR Cross Area
Improving Reliability of Fine-tuning with Block-wise Optimisation
In our work, the layer selection can be done in four different ways.
SAH: Shifting-aware Asymmetric Hashing for Reverse $k$-Maximum Inner Product Search
To speed up the Maximum Inner Product Search (MIPS) on item vectors, we design a shifting-invariant asymmetric transformation and develop a novel sublinear-time Shifting-Aware Asymmetric Locality Sensitive Hashing (SA-ALSH) scheme.
A General Unified Graph Neural Network Framework Against Adversarial Attacks
The other is the convolution operation for features to find the optimal solution adopting the Laplacian smoothness and the prior knowledge that nodes with many neighbors are difficult to attack.
Unsupervised Abstract Reasoning for Raven's Problem Matrices
Raven's Progressive Matrices (RPM) is highly correlated with human intelligence, and it has been widely used to measure the abstract reasoning ability of humans.
T-vectors: Weakly Supervised Speaker Identification Using Hierarchical Transformer Model
The use of memory mechanism could reach 10. 6% and 7. 7% relative improvement compared with not using memory mechanism.
Exploration of Audio Quality Assessment and Anomaly Localisation Using Attention Models
The first task is to predict an utterance quality score, and the second is to identify where an anomalous distortion takes place in a recording.
Speaker Re-identification with Speaker Dependent Speech Enhancement
The obtained results show that the proposed approach using speaker dependent speech enhancement can yield better speaker recognition and speech enhancement performances than two baselines in various noise conditions.
Weakly Supervised Training of Hierarchical Attention Networks for Speaker Identification
To evaluate the effectiveness of the proposed approach, artificial datasets based on Switchboard Cellular part1 (SWBC) and Voxceleb1 are constructed in two conditions, where speakers' voices are overlapped and not overlapped.
GraphLIME: Local Interpretable Model Explanations for Graph Neural Networks
In this paper, we propose GraphLIME, a local interpretable model explanation for graphs using the Hilbert-Schmidt Independence Criterion (HSIC) Lasso, which is a nonlinear feature selection method.
Robust Speaker Recognition Using Speech Enhancement And Attention Model
Instead of individually processing speech enhancement and speaker recognition, the two modules are integrated into one framework by a joint optimisation using deep neural networks.
Multi-task Sentence Encoding Model for Semantic Retrieval in Question Answering Systems
Sentence matching is an essential task in the QA systems and is usually reformulated as a Paraphrase Identification (PI) problem.
Ranked #13 on
Paraphrase Identification
on Quora Question Pairs
(Accuracy metric)
H-VECTORS: Utterance-level Speaker Embedding Using A Hierarchical Attention Model
In the proposed approach, frame-level encoder and attention are applied on segments of an input utterance and generate individual segment vectors.
Improving Noise Robustness In Speaker Identification Using A Two-Stage Attention Model
While the use of deep neural networks has significantly boosted speaker recognition performance, it is still challenging to separate speakers in poor acoustic environments.
A Joint Model for Aspect-Category Sentiment Analysis with Shared Sentiment Prediction Layer
Aspect-category sentiment analysis (ACSA) aims to predict the aspect categories mentioned in texts and their corresponding sentiment polarities.
Attention and Localization based on a Deep Convolutional Recurrent Model for Weakly Supervised Audio Tagging
Audio tagging aims to perform multi-label classification on audio chunks and it is a newly proposed task in the Detection and Classification of Acoustic Scenes and Events 2016 (DCASE 2016) challenge.
Sound
Convolutional Gated Recurrent Neural Network Incorporating Spatial Features for Audio Tagging
In this paper, we propose to use a convolutional neural network (CNN) to extract robust features from mel-filter banks (MFBs), spectrograms or even raw waveforms for audio tagging.
Hierarchical learning for DNN-based acoustic scene classification
In this paper, we present a deep neural network (DNN)-based acoustic scene classification framework.
Unsupervised Feature Learning Based on Deep Models for Environmental Audio Tagging
For the unsupervised feature learning, we propose to use a symmetric or asymmetric deep de-noising auto-encoder (sDAE or aDAE) to generate new data-driven features from the Mel-Filter Banks (MFBs) features.
Fully DNN-based Multi-label regression for audio tagging
Compared with the conventional Gaussian Mixture Model (GMM) and support vector machine (SVM) methods, the proposed fully DNN-based method could well utilize the long-term temporal information with the whole chunk as the input.
