Search Results for author:
Found 17 papers, 7 papers with code
Learn2Talk: 3D Talking Face Learns from 2D Talking Face
Speech-driven facial animation methods usually contain two main classes, 3D and 2D talking face, both of which attract considerable research attention in recent years.
Learning from Graphs with Heterophily: Progress and Future
Graphs are structured data that models complex relations between real-world entities.
InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks
In this paper, we introduce InfiAgent-DABench, the first benchmark specifically designed to evaluate LLM-based agents on data analysis tasks.
Self-supervised Heterogeneous Graph Variational Autoencoders
Instead of directly reconstructing raw features for attributed nodes, SHAVA generates the initial low-dimensional representation matrix for all the nodes, based on which raw features of attributed nodes are further reconstructed to leverage accurate attributes.
Prioritized Propagation in Graph Neural Networks
Specifically, the framework consists of three components: a backbone GNN model, a propagation controller to determine the optimal propagation steps for nodes, and a weight controller to compute the priority scores for nodes.
Label Propagation for Graph Label Noise
In this paper, we study graph label noise in the context of arbitrary heterophily, with the aim of rectifying noisy labels and assigning labels to previously unlabeled nodes.
Graph Self-Contrast Representation Learning
Further, Since the triplet loss only optimizes the relative distance between the anchor and its positive/negative samples, it is difficult to ensure the absolute distance between the anchor and positive sample.
Edge Deep Learning Model Protection via Neuron Authorization
With the development of deep learning processors and accelerators, deep learning models have been widely deployed on edge devices as part of the Internet of Things.
Super-resolution Reconstruction of Single Image for Latent features
Single-image super-resolution (SISR) typically focuses on restoring various degraded low-resolution (LR) images to a single high-resolution (HR) image.
Rethinking the Defense Against Free-rider Attack From the Perspective of Model Weight Evolving Frequency
To address these challenges, we reconsider the defense from a novel perspective, i. e., model weight evolving frequency. Empirically, we gain a novel insight that during the FL's training, the model weight evolving frequency of free-riders and that of benign clients are significantly different.
Finding Global Homophily in Graph Neural Networks When Meeting Heterophily
Further, for other homophilous nodes excluded in the neighborhood, they are ignored for information aggregation.
Ranked #2 on
Node Classification
on pokec
Excitement Surfeited Turns to Errors: Deep Learning Testing Framework Based on Excitable Neurons
By maximizing the number of excitable neurons concerning various wrong behaviors of models, DeepSensor can generate testing examples that effectively trigger more errors due to adversarial inputs, polluted data and incomplete training.
NeuronFair: Interpretable White-Box Fairness Testing through Biased Neuron Identification
To overcome the challenges, we propose NeuronFair, a new DNN fairness testing framework that differs from previous work in several key aspects: (1) interpretable - it quantitatively interprets DNNs' fairness violations for the biased decision; (2) effective - it uses the interpretation results to guide the generation of more diverse instances in less time; (3) generic - it can handle both structured and unstructured data.
CatchBackdoor: Backdoor Testing by Critical Trojan Neural Path Identification via Differential Fuzzing
Existing DNN testing methods are mainly designed to find incorrect corner case behaviors in adversarial settings but fail to discover the backdoors crafted by strong trojan attacks.
Where Does the Robustness Come from? A Study of the Transformation-based Ensemble Defence
This paper aims to provide a thorough study on the effectiveness of the transformation-based ensemble defence for image classification and its reasons.
DeepMnemonic: Password Mnemonic Generation via Deep Attentive Encoder-Decoder Model
Moreover, the user study further validates that the generated mnemonic sentences by DeepMnemonic are useful in helping users memorize strong passwords.
Combining Global Models for Parsing Universal Dependencies
We describe our entry, C2L2, to the CoNLL 2017 shared task on parsing Universal Dependencies from raw text.
