Search Results for author:
Found 25 papers, 7 papers with code
Source-Target Similarity Modelings for Multi-Source Transfer Gaussian Process Regression
A key challenge in multi-source transfer learning is to capture the diverse inter-domain similarities.
Minimalistic Attacks: How Little it Takes to Fool a Deep Reinforcement Learning Policy
Recent studies have revealed that neural network-based policies can be easily fooled by adversarial examples.
Causal Modeling with Stochastic Confounders
This work extends causal inference with stochastic confounders.
Subdomain Adaptation with Manifolds Discrepancy Alignment
Specifically, we propose to use low-dimensional manifold to represent subdomain, and align the local data distribution discrepancy in each manifold across domains.
Hierarchical Reinforcement Learning in StarCraft II with Human Expertise in Subgoals Selection
This work is inspired by recent advances in hierarchical reinforcement learning (HRL) (Barto and Mahadevan 2003; Hengst 2010), and improvements in learning efficiency from heuristic-based subgoal selection, experience replay (Lin 1993; Andrychowicz et al. 2017), and task-based curriculum learning (Bengio et al. 2009; Zaremba and Sutskever 2014).
MESA: Boost Ensemble Imbalanced Learning with MEta-SAmpler
This makes MESA generally applicable to most of the existing learning models and the meta-sampler can be efficiently applied to new tasks.
Cooperative Heterogeneous Deep Reinforcement Learning
Numerous deep reinforcement learning agents have been proposed, and each of them has its strengths and flaws.
An Improved Transfer Model: Randomized Transferable Machine
Existing studies usually assume that the learned new feature representation is \emph{domain-invariant}, and thus train a transfer model $\mathcal{M}$ on the source domain.
Learning Disentangled Semantic Representation for Domain Adaptation
Different from previous efforts on the entangled feature space, we aim to extract the domain invariant semantic information in the latent disentangled semantic representation (DSR) of the data.
Joint Intent Detection and Slot Filling with Wheel-Graph Attention Networks
In this paper, we propose a new joint model with a wheel-graph attention network (Wheel-GAT) which is able to model interrelated connections directly for intent detection and slot filling.
Adaptive Multi-Source Causal Inference
The proposed method can infer causal effects in the target population without prior knowledge of data discrepancy between the additional data sources and the target.
Graph Domain Adaptation: A Generative View
Based on this assumption, we propose a disentanglement-based unsupervised domain adaptation method for the graph-structured data, which applies variational graph auto-encoders to recover these latent variables and disentangles them via three supervised learning modules.
Synthesising Audio Adversarial Examples for Automatic Speech Recognition
Adversarial examples in automatic speech recognition (ASR) are naturally sounded by humans yet capable of fooling well trained ASR models to transcribe incorrectly.
Uncertainty Regularized Policy Learning for Offline Reinforcement Learning
URPL adds an uncertainty regularization term in the policy learning objective to enforce to learn a more stable policy under the offline setting.
Adaptive Q-learning for Interaction-Limited Reinforcement Learning
Specifically, we explicitly consider the difference between the online and offline data and apply an adaptive update scheme accordingly, i. e., a pessimistic update strategy for the offline dataset and a greedy or no pessimistic update scheme for the online dataset.
Handling Inter-class and Intra-class Imbalance in Class-imbalanced Learning
Class-imbalance is a common problem in machine learning practice.
Language Adaptive Cross-lingual Speech Representation Learning with Sparse Sharing Sub-networks
It makes room for language specific modeling by pruning out unimportant parameters for each language, without requiring any manually designed language specific component.
Unsupervised Video Domain Adaptation for Action Recognition: A Disentanglement Perspective
Specifically, we consider the generation of cross-domain videos from two sets of latent factors, one encoding the static information and another encoding the dynamic information.
Importance Prioritized Policy Distillation
Given such an issue, we denote the \emph{frame importance} as its contribution to the expected reward on a particular frame, and hypothesize that adapting such frame importance could benefit the performance of the distilled student policy.
Multi-objective optimization via evolutionary algorithm (MOVEA) for high-definition transcranial electrical stimulation of the human brain
In this paper, we propose a general framework called multi-objective optimization via evolutionary algorithms (MOVEA) to address the non-convex optimization problem in designing TES strategies without predefined direction.
Virtual Try-On with Pose-Garment Keypoints Guided Inpainting
In our method, human pose and garment keypoints are extracted from source images and constructed as graphs to predict the garment keypoints at the target pose.
Adaptive Policy Learning for Offline-to-Online Reinforcement Learning
In this paper, we consider an offline-to-online setting where the agent is first learned from the offline dataset and then trained online, and propose a framework called Adaptive Policy Learning for effectively taking advantage of offline and online data.
Mega-TTS 2: Boosting Prompting Mechanisms for Zero-Shot Speech Synthesis
However, the prompting mechanisms of zero-shot TTS still face challenges in the following aspects: 1) previous works of zero-shot TTS are typically trained with single-sentence prompts, which significantly restricts their performance when the data is relatively sufficient during the inference stage.
SR-R$^2$KAC: Improving Single Image Defocus Deblurring
To further alleviate the contingent effect of recursive stacking, i. e., ringing artifacts, we add identity shortcuts between atrous convolutions to simulate residual deconvolutions.
C2G2: Controllable Co-speech Gesture Generation with Latent Diffusion Model
Co-speech gesture generation is crucial for automatic digital avatar animation.
