Search Results for author:
Found 27 papers, 6 papers with code
MG-BERT: Multi-Graph Augmented BERT for Masked Language Modeling
Pre-trained models like Bidirectional Encoder Representations from Transformers (BERT), have recently made a big leap forward in Natural Language Processing (NLP) tasks.
Khayyam Challenge (PersianMMLU): Is Your LLM Truly Wise to The Persian Language?
Evaluating Large Language Models (LLMs) is challenging due to their generative nature, necessitating precise evaluation methodologies.
Language Plays a Pivotal Role in the Object-Attribute Compositional Generalization of CLIP
Vision-language models, such as CLIP, have shown promising Out-of-Distribution (OoD) generalization under various types of distribution shifts.
Decompose-and-Compose: A Compositional Approach to Mitigating Spurious Correlation
Based on our observations, models trained with ERM usually highly attend to either the causal components or the components having a high spurious correlation with the label (especially in datapoints on which models have a high confidence).
Annotation-Free Group Robustness via Loss-Based Resampling
In order to provide group robustness without such annotations, we propose a new method, called loss-based feature re-weighting (LFR), in which we infer a grouping of the data by evaluating an ERM-pre-trained model on a small left-out split of the training data.
Predicting risk/reward ratio in financial markets for asset management using machine learning
Financial market forecasting remains a formidable challenge despite the surge in computational capabilities and machine learning advancements.
A Distinct Unsupervised Reference Model From The Environment Helps Continual Learning
The existing continual learning methods are mainly focused on fully-supervised scenarios and are still not able to take advantage of unlabeled data available in the environment.
BIMRL: Brain Inspired Meta Reinforcement Learning
Inspired by recent progress in meta-RL, we introduce BIMRL, a novel multi-layer architecture along with a novel brain-inspired memory module that will help agents quickly adapt to new tasks within a few episodes.
SCGG: A Deep Structure-Conditioned Graph Generative Model
Deep learning-based graph generation approaches have remarkable capacities for graph data modeling, allowing them to solve a wide range of real-world problems.
Isoform Function Prediction Using a Deep Neural Network
Most studies have shown that alternative splicing plays a significant role in human health and disease.
HEROHE Challenge: assessing HER2 status in breast cancer without immunohistochemistry or in situ hybridization
Breast cancer is the most common malignancy in women, being responsible for more than half a million deaths every year.
CCGG: A Deep Autoregressive Model for Class-Conditional Graph Generation
With an increase in the number of applications where data is represented as graphs, the problem of graph generation has recently become a hot topic.
SOInter: A Novel Deep Energy-Based Interpretation Method for Explaining Structured Output Models
Because of the complex relationship between the computational path of output variables in structured models, a feature can affect the value of output through other ones.
Rate-Distortion Analysis of Minimum Excess Risk in Bayesian Learning
For the upper bound, the optimization is further constrained to use $R$ bits from the training set, a setting which relates MER to information-theoretic bounds on the generalization gap in frequentist learning.
RA-GCN: Graph Convolutional Network for Disease Prediction Problems with Imbalanced Data
This is accomplished by associating a graph-based neural network to each class, which is responsible for weighting the class samples and changing the importance of each sample for the classifier.
Semi-Supervised Disentanglement of Class-Related and Class-Independent Factors in VAE
We address this problem by proposing a framework capable of disentangling class-related and class-independent factors of variation in data.
Deep Graph Generators: A Survey
Deep generative models have achieved great success in areas such as image, speech, and natural language processing in the past few years.
Paraphrase Generation by Learning How to Edit from Samples
With its novel editor module, the model then paraphrases the input sequence by editing it using the extracted relations between the retrieved pair of sentences.
DGSAN: Discrete Generative Self-Adversarial Network
The proposed method has an iterative manner in which each new generator is definedbased on the last discriminator.
Jointly Measuring Diversity and Quality in Text Generation Models
In this paper, we propose metrics to evaluate both the quality and diversity simultaneously by approximating the distance of the learned generative model and the real data distribution.
Adversarial Classifier for Imbalanced Problems
However, this approach has not been extensively utilized for classifier training.
MGCN: Semi-supervised Classification in Multi-layer Graphs with Graph Convolutional Networks
The goal of graph embedding is to find a low dimensional representation of graph nodes that preserves the graph information.
An Efficient Large-scale Semi-supervised Multi-label Classifier Capable of Handling Missing labels
Multi-label classifiers have to address many problems including: handling large-scale datasets with many instances and a large set of labels, compensating missing label assignments in the training set, considering correlations between labels, as well as exploiting unlabeled data to improve prediction performance.
Semi-supervised Zero-Shot Learning by a Clustering-based Approach
We seek a linear transformation on signatures to map them onto the visual features, such that the mapped signatures of the seen classes are close to labeled samples of the corresponding classes and unlabeled data are also close to the mapped signatures of one of the unseen classes.
Selecting Efficient Features via a Hyper-Heuristic Approach
Hyper-heuristic is a new heuristic approach which can search the solution space effectively by applying local searches appropriately.
Hyper-Heuristic Algorithm for Finding Efficient Features in Diagnose of Lung Cancer Disease
In our study, new method is proposed for identify efficient features of lung cancer.
Active Distance-Based Clustering using K-medoids
k-medoids algorithm is a partitional, centroid-based clustering algorithm which uses pairwise distances of data points and tries to directly decompose the dataset with $n$ points into a set of $k$ disjoint clusters.
