Search Results for author:
Found 54 papers, 22 papers with code
Self-Supervised Graph Transformer on Large-Scale Molecular Data
We pre-train GROVER with 100 million parameters on 10 million unlabelled molecules -- the biggest GNN and the largest training dataset in molecular representation learning.
Ranked #4 on
Molecular Property Prediction
on QM7
Adversarial Sparse Transformer for Time Series Forecasting
Specifically, AST adopts a Sparse Transformer as the generator to learn a sparse attention map for time series forecasting, and uses a discriminator to improve the prediction performance from sequence level.
Multivariate Time Series Forecasting
Probabilistic Time Series Forecasting
+1
Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective
We aim at advancing blind image quality assessment (BIQA), which predicts the human perception of image quality without any reference information.
Hierarchical Attention Transfer Network for Cross-Domain Sentiment Classification
Existing cross-domain sentiment classification meth- ods cannot automatically capture non-pivots, i. e., the domain- specific sentiment words, and pivots, i. e., the domain-shared sentiment words, simultaneously.
Transferable End-to-End Aspect-based Sentiment Analysis with Selective Adversarial Learning
Joint extraction of aspects and sentiments can be effectively formulated as a sequence labeling problem.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+1
Hierarchically Structured Meta-learning
In order to learn quickly with few samples, meta-learning utilizes prior knowledge learned from previous tasks.
Learning from Multiple Cities: A Meta-Learning Approach for Spatial-Temporal Prediction
Specifically, our proposed model is designed as a spatial-temporal network with a meta-learning paradigm.
Exploiting Coarse-to-Fine Task Transfer for Aspect-level Sentiment Classification
Aspect-level sentiment classification (ASC) aims at identifying sentiment polarities towards aspects in a sentence, where the aspect can behave as a general Aspect Category (AC) or a specific Aspect Term (AT).
Graph Few-shot Learning via Knowledge Transfer
Towards the challenging problem of semi-supervised node classification, there have been extensive studies.
FGAHOI: Fine-Grained Anchors for Human-Object Interaction Detection
HSAM and TAM semantically align and merge the extracted features and query embeddings in the hierarchical spatial and task perspectives in turn.
Ranked #6 on
Human-Object Interaction Detection
on HICO-DET
Improving Generalization in Meta-learning via Task Augmentation
Moreover, both MetaMix and Channel Shuffle outperform state-of-the-art results by a large margin across many datasets and are compatible with existing meta-learning algorithms.
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.
Collaborative Unsupervised Domain Adaptation for Medical Image Diagnosis
In this paper, we seek to exploit rich labeled data from relevant domains to help the learning in the target task with unsupervised domain adaptation (UDA).
COVID-DA: Deep Domain Adaptation from Typical Pneumonia to COVID-19
There are two main challenges: 1) the discrepancy of data distributions between domains; 2) the task difference between the diagnosis of typical pneumonia and COVID-19.
Collaborative Unsupervised Domain Adaptation for Medical Image Diagnosis
Deep learning based medical image diagnosis has shown great potential in clinical medicine.
Fisher Deep Domain Adaptation
Though the learned representations are separable in the source domain, they usually have a large variance and samples with different class labels tend to overlap in the target domain, which yields suboptimal adaptation performance.
Detecting the open-world objects with the help of the Brain
We propose leveraging the VL as the ``Brain'' of the open-world detector by simply generating unknown labels.
SKDF: A Simple Knowledge Distillation Framework for Distilling Open-Vocabulary Knowledge to Open-world Object Detector
Ablation experiments demonstrate that both of them are effective in mitigating the impact of open-world knowledge distillation on the learning of known objects.
Learning to Substitute Spans towards Improving Compositional Generalization
Despite the rising prevalence of neural sequence models, recent empirical evidences suggest their deficiency in compositional generalization.
Towards Anytime Fine-tuning: Continually Pre-trained Language Models with Hypernetwork Prompt
In this work, we first investigate such anytime fine-tuning effectiveness of existing continual pre-training approaches, concluding with unanimously decreased performance on unseen domains.
Unleashing the Power of Meta-tuning for Few-shot Generalization Through Sparse Interpolated Experts
Conventional wisdom suggests parameter-efficient fine-tuning of foundation models as the state-of-the-art method for transfer learning in vision, replacing the rich literature of alternatives such as meta-learning.
Benchmarking and Improving Compositional Generalization of Multi-aspect Controllable Text Generation
Compositional generalization, representing the model's ability to generate text with new attribute combinations obtained by recombining single attributes from the training data, is a crucial property for multi-aspect controllable text generation (MCTG) methods.
Learning to Multitask
Based on such training set, L2MT first uses a proposed layerwise graph neural network to learn task embeddings for all the tasks in a multitask problem and then learns an estimation function to estimate the relative test error based on task embeddings and the representation of the multitask model based on a unified formulation.
Learning to Transfer
We establish the L2T framework in two stages: 1) we first learn a reflection function encrypting transfer learning skills from experiences; and 2) we infer what and how to transfer for a newly arrived pair of domains by optimizing the reflection function.
Transfer Learning via Learning to Transfer
In transfer learning, what and how to transfer are two primary issues to be addressed, as different transfer learning algorithms applied between a source and a target domain result in different knowledge transferred and thereby the performance improvement in the target domain.
Transferable Neural Processes for Hyperparameter Optimization
Automated machine learning aims to automate the whole process of machine learning, including model configuration.
Infant brain MRI segmentation with dilated convolution pyramid downsampling and self-attention
In this paper, we propose a dual aggregation network to adaptively aggregate different information in infant brain MRI segmentation.
Large-Scale Screening of COVID-19 from Community Acquired Pneumonia using Infection Size-Aware Classification
The worldwide spread of coronavirus disease (COVID-19) has become a threatening risk for global public health.
Dual-Sampling Attention Network for Diagnosis of COVID-19 from Community Acquired Pneumonia
To this end, we develop a dual-sampling attention network to automatically diagnose COVID- 19 from the community acquired pneumonia (CAP) in chest computed tomography (CT).
Adaptive Feature Selection Guided Deep Forest for COVID-19 Classification with Chest CT
We evaluated our proposed AFS-DF on COVID-19 dataset with 1495 patients of COVID-19 and 1027 patients of community acquired pneumonia (CAP).
Hypergraph Learning for Identification of COVID-19 with CT Imaging
The main challenge in early screening is how to model the confusing cases in the COVID-19 and CAP groups, with very similar clinical manifestations and imaging features.
Multi-Site Infant Brain Segmentation Algorithms: The iSeg-2019 Challenge
Deep learning-based methods have achieved state-of-the-art performance; however, one of major limitations is that the learning-based methods may suffer from the multi-site issue, that is, the models trained on a dataset from one site may not be applicable to the datasets acquired from other sites with different imaging protocols/scanners.
Learn to Cross-lingual Transfer with Meta Graph Learning Across Heterogeneous Languages
Recent emergence of multilingual pre-training language model (mPLM) has enabled breakthroughs on various downstream cross-lingual transfer (CLT) tasks.
A novel multiple instance learning framework for COVID-19 severity assessment via data augmentation and self-supervised learning
How to fast and accurately assess the severity level of COVID-19 is an essential problem, when millions of people are suffering from the pandemic around the world.
Frustratingly Easy Transferability Estimation
Transferability estimation has been an essential tool in selecting a pre-trained model and the layers in it for transfer learning, to transfer, so as to maximize the performance on a target task and prevent negative transfer.
Cross-Site Severity Assessment of COVID-19 from CT Images via Domain Adaptation
Particularly, we propose a domain translator and align the heterogeneous data to the estimated class prototypes (i. e., class centers) in a hyper-sphere manifold.
Minimizing Memorization in Meta-learning: A Causal Perspective
Meta-learning has emerged as a potent paradigm for quick learning of few-shot tasks, by leveraging the meta-knowledge learned from meta-training tasks.
MetaTS: Meta Teacher-Student Network for Multilingual Sequence Labeling with Minimal Supervision
In this work, we explore multilingual sequence labeling with minimal supervision using a single unified model for multiple languages.
Functionally Regionalized Knowledge Transfer for Low-resource Drug Discovery
More recently, there has been a surge of interest in employing machine learning approaches to expedite the drug discovery process where virtual screening for hit discovery and ADMET prediction for lead optimization play essential roles.
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.
Discriminative-Region Attention and Orthogonal-View Generation Model for Vehicle Re-Identification
Finally, the distance between vehicle appearances is presented by the discriminative region features and multi-view features together.
Learning to generate imaginary tasks for improving generalization in meta-learning
The success of meta-learning on existing benchmarks is predicated on the assumption that the distribution of meta-training tasks covers meta-testing tasks.
Wasserstein Distributional Learning
To overcome this fundamental issue, we propose Wasserstein Distributional Learning (WDL), a flexible density-on-scalar regression modeling framework that starts with the Wasserstein distance $W_2$ as a proper metric for the space of density outcomes.
Disentangling Task Relations for Few-shot Text Classification via Self-Supervised Hierarchical Task Clustering
However, most prior works assume that all the tasks are sampled from a single data source, which cannot adapt to real-world scenarios where tasks are heterogeneous and lie in different distributions.
Hybrid Censored Quantile Regression Forest to Assess the Heterogeneous Effects
We propose a variable importance decomposition to measure the impact of a variable on the treatment effect function.
CAT: LoCalization and IdentificAtion Cascade Detection Transformer for Open-World Object Detection
Open-world object detection (OWOD), as a more general and challenging goal, requires the model trained from data on known objects to detect both known and unknown objects and incrementally learn to identify these unknown objects.
On the Opportunities of Green Computing: A Survey
To tackle the challenges of computing resources and environmental impact of AI, Green Computing has become a hot research topic.
High-fidelity 3D Reconstruction of Plants using Neural Radiance Field
Recently, a promising development has emerged in the form of Neural Radiance Field (NeRF), a novel method that utilises neural density fields.
Concept-wise Fine-tuning Matters in Preventing Negative Transfer
A multitude of prevalent pre-trained models mark a major milestone in the development of artificial intelligence, while fine-tuning has been a common practice that enables pretrained models to figure prominently in a wide array of target datasets.
RetroOOD: Understanding Out-of-Distribution Generalization in Retrosynthesis Prediction
Machine learning-assisted retrosynthesis prediction models have been gaining widespread adoption, though their performances oftentimes degrade significantly when deployed in real-world applications embracing out-of-distribution (OOD) molecules or reactions.
Understanding the Multi-modal Prompts of the Pre-trained Vision-Language Model
In this paper, we conduct a direct analysis of the multi-modal prompts by asking the following questions: $(i)$ How do the learned multi-modal prompts improve the recognition performance?
From Words to Molecules: A Survey of Large Language Models in Chemistry
After that, we explore the diverse applications of LLMs in chemistry, including novel paradigms for their application in chemistry tasks.
Understanding and Patching Compositional Reasoning in LLMs
LLMs have marked a revolutonary shift, yet they falter when faced with compositional reasoning tasks.
MoPE-CLIP: Structured Pruning for Efficient Vision-Language Models with Module-wise Pruning Error Metric
We find that directly using smaller pre-trained models and applying magnitude-based pruning on CLIP models leads to inflexibility and inferior performance.
