Search Results for author:
Found 32 papers, 16 papers with code
Pre-trained Vision and Language Transformers Are Few-Shot Incremental Learners
In this paper, we argue that large models such as vision and language transformers pre-trained on large datasets can be excellent few-shot incremental learners.
Mitigating the Linguistic Gap with Phonemic Representations for Robust Multilingual Language Understanding
Approaches to improving multilingual language understanding often require multiple languages during the training phase, rely on complicated training techniques, and -- importantly -- struggle with significant performance gaps between high-resource and low-resource languages.
Towards Calibrated Robust Fine-Tuning of Vision-Language Models
Robust fine-tuning aims to ensure performance on out-of-distribution (OOD) samples, which is sometimes compromised by pursuing adaptation on in-distribution (ID) samples.
Leveraging Skill-to-Skill Supervision for Knowledge Tracing
To do so, knowledge tracing systems should trace the knowledge state of the students by utilizing their problem-solving history and knowledge about the problems.
RPLKG: Robust Prompt Learning with Knowledge Graph
To improve the generalization performance on few-shot learning, there have been diverse efforts, such as prompt learning and adapter.
BlackVIP: Black-Box Visual Prompting for Robust Transfer Learning
In this work, we propose black-box visual prompting (BlackVIP), which efficiently adapts the PTMs without knowledge about model architectures and parameters.
Causally Disentangled Generative Variational AutoEncoder
We present a new supervised learning technique for the Variational AutoEncoder (VAE) that allows it to learn a causally disentangled representation and generate causally disentangled outcomes simultaneously.
SAAL: Sharpness-Aware Active Learning
Specifically, our proposed method, Sharpness-Aware Active Learning (SAAL), constructs its acquisition function by selecting unlabeled instances whose perturbed loss becomes maximum.
Sufficient Invariant Learning for Distribution Shift
Moreover, we propose a new algorithm, Adaptive Sharpness-aware Group Distributionally Robust Optimization (ASGDRO), to learn sufficient invariant features across domains or groups.
Graph Perceiver IO: A General Architecture for Graph Structured Data
A graph has an adjacency matrix different from other dataset domains such as text and image, and it is not trivial to handle the topological information, relational information, and canonical positional information.
Learning Fair Representation via Distributional Contrastive Disentanglement
We provide a new type of contrastive loss motivated by Gaussian and Student-t kernels for distributional contrastive learning with theoretical analysis.
Unknown-Aware Domain Adversarial Learning for Open-Set Domain Adaptation
Therefore, we propose Unknown-Aware Domain Adversarial Learning (UADAL), which $\textit{aligns}$ the source and the target-$\textit{known}$ distribution while simultaneously $\textit{segregating}$ the target-$\textit{unknown}$ distribution in the feature alignment procedure.
From Noisy Prediction to True Label: Noisy Prediction Calibration via Generative Model
We suggest a new branch of method, Noisy Prediction Calibration (NPC) in learning with noisy labels.
Geodesic Multi-Modal Mixup for Robust Fine-Tuning
Such a lack of alignment and uniformity might restrict the transferability and robustness of embeddings.
High Precision Score-based Diffusion Models
From the theory side, the difficulty arises in estimating the high precision diffusion because the data score goes to $\infty$ as $t \rightarrow 0$ of the diffusion time.
Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation
This paper investigates with sufficient empirical evidence that such inverse correlation happens because density estimation is significantly contributed by small diffusion time, whereas sample generation mainly depends on large diffusion time.
Ranked #2 on
Image Generation
on CIFAR-10
(Inception score metric)
LADA: Look-Ahead Data Acquisition via Augmentation for Deep Active Learning
Active learning effectively collects data instances for training deep learning models when the labeled dataset is limited and the annotation cost is high.
Neural Posterior Regularization for Likelihood-Free Inference
A simulation is useful when the phenomenon of interest is either expensive to regenerate or irreproducible with the same context.
Counterfactual Fairness with Disentangled Causal Effect Variational Autoencoder
Therefore, this paper proposes Disentangled Causal Effect Variational Autoencoder (DCEVAE) to resolve this limitation by disentangling the exogenous uncertainty into two latent variables: either 1) independent to interventions or 2) correlated to interventions without causality.
LADA: Look-Ahead Data Acquisition via Augmentation for Active Learning
Active learning effectively collects data instances for training deep learning models when the labeled dataset is limited and the annotation cost is high.
Neutralizing Gender Bias in Word Embeddings with Latent Disentanglement and Counterfactual Generation
Recent research demonstrates that word embeddings, trained on the human-generated corpus, have strong gender biases in embedding spaces, and these biases can result in the discriminative results from the various downstream tasks.
Sequential Likelihood-Free Inference with Neural Proposal
This paper introduces a new sampling approach, called Neural Proposal (NP), of the simulation input that resolves the biased data collection as it guarantees the i. i. d.
Approximate Inference for Spectral Mixture Kernel
To improve the training, we propose an approximate Bayesian inference for the SM kernel.
Implicit Kernel Attention
For the attention in Transformer and GAT, we derive that the attention is a product of two parts: 1) the RBF kernel to measure the similarity of two instances and 2) the exponential of $L^{2}$ norm to compute the importance of individual instances.
Adversarial Likelihood-Free Inference on Black-Box Generator
Generative Adversarial Network (GAN) can be viewed as an implicit estimator of a data distribution, and this perspective motivates using the adversarial concept in the true input parameter estimation of black-box generators.
Neutralizing Gender Bias in Word Embedding with Latent Disentanglement and Counterfactual Generation
Recent research demonstrates that word embeddings, trained on the human-generated corpus, have strong gender biases in embedding spaces, and these biases can result in the discriminative results from the various downstream tasks.
Sequential Recommendation with Relation-Aware Kernelized Self-Attention
This work merges the self-attention of the Transformer and the sequential recommendation by adding a probabilistic model of the recommendation task specifics.
Bivariate Beta-LSTM
Long Short-Term Memory (LSTM) infers the long term dependency through a cell state maintained by the input and the forget gate structures, which models a gate output as a value in [0, 1] through a sigmoid function.
Neural Ideal Point Estimation Network
Understanding politics is challenging because the politics take the influence from everything.
Hierarchical Context enabled Recurrent Neural Network for Recommendation
The analyses on the user history require the robust sequential model to anticipate the transitions and the decays of user interests.
Adversarial Dropout for Recurrent Neural Networks
Successful application processing sequential data, such as text and speech, requires an improved generalization performance of recurrent neural networks (RNNs).
Hierarchically Clustered Representation Learning
The joint optimization of representation learning and clustering in the embedding space has experienced a breakthrough in recent years.
