Search Results for author:
Found 105 papers, 52 papers with code
CLAD: Robust Audio Deepfake Detection Against Manipulation Attacks with Contrastive Learning
The detection models exhibited vulnerabilities, with FAR rising to 36. 69%, 31. 23%, and 51. 28% under volume control, fading, and noise injection, respectively.
FABind+: Enhancing Molecular Docking through Improved Pocket Prediction and Pose Generation
Molecular docking is a pivotal process in drug discovery.
Benchmarks and Challenges in Pose Estimation for Egocentric Hand Interactions with Objects
We interact with the world with our hands and see it through our own (egocentric) perspective.
Rolling bearing fault diagnosis method based on generative adversarial enhanced multi-scale convolutional neural network model
Firstly, Gram angular field coding technique is used to encode the time domain signal of the rolling bearing and generate the feature map to retain the complete information of the vibration signal.
Revisiting Edge Perturbation for Graph Neural Network in Graph Data Augmentation and Attack
It can be categorized into two veins based on their effects on the performance of graph neural networks (GNNs), i. e., graph data augmentation and attack.
Boosting Meta-Training with Base Class Information for Few-Shot Learning
However, as a non-end-to-end training method, indicating the meta-training stage can only begin after the completion of pre-training, Meta-Baseline suffers from higher training cost and suboptimal performance due to the inherent conflicts of the two training stages.
An Effective Branch-and-Bound Algorithm with New Bounding Methods for the Maximum $s$-Bundle Problem
Exact algorithms for MBP mainly follow the branch-and-bound (BnB) framework, whose performance heavily depends on the quality of the upper bound on the cardinality of a maximum s-bundle and the initial lower bound with graph reduction.
CORE: Mitigating Catastrophic Forgetting in Continual Learning through Cognitive Replay
The former adaptively modulates the replay buffer allocation for each task based on its forgetting rate, while the latter guarantees the inclusion of representative data that best encapsulates the characteristics of each task within the buffer.
Fast Adversarial Training against Textual Adversarial Attacks
Based on the observation that the adversarial perturbations crafted by single-step and multi-step gradient ascent are similar, FAT uses single-step gradient ascent to craft adversarial examples in the embedding space to expedite the training process.
Rethinking the Soft Conflict Pseudo Boolean Constraint on MaxSAT Local Search Solvers
In this paper, we propose to transfer the SPB constraint into the clause weighting system of the local search method, leading the algorithm to better solutions.
AutoAugment Input Transformation for Highly Transferable Targeted Attacks
However, few of them are dedicated to input transformation. In this work, we observe a positive correlation between the logit/probability of the target class and diverse input transformation methods in targeted attacks.
BCN: Batch Channel Normalization for Image Classification
Normalization techniques have been widely used in the field of deep learning due to their capability of enabling higher learning rates and are less careful in initialization.
Diversified Node Sampling based Hierarchical Transformer Pooling for Graph Representation Learning
Graph pooling methods have been widely used on downsampling graphs, achieving impressive results on multiple graph-level tasks like graph classification and graph generation.
SignGT: Signed Attention-based Graph Transformer for Graph Representation Learning
In this way, SignGT could learn informative node representations from both long-range dependencies and local topology information.
Ranked #4 on
Node Classification
on Actor
FABind: Fast and Accurate Protein-Ligand Binding
In this work, we propose $\mathbf{FABind}$, an end-to-end model that combines pocket prediction and docking to achieve accurate and fast protein-ligand binding.
Long-range Meta-path Search on Large-scale Heterogeneous Graphs
To this end, we investigate the importance of different meta-paths and introduce an automatic framework for utilizing long-range dependency on heterogeneous graphs, denoted as Long-range Meta-path Search through Progressive Sampling (LMSPS).
Ranked #2 on
Node Property Prediction
on ogbn-mag
Sampling-based Fast Gradient Rescaling Method for Highly Transferable Adversarial Attacks
In either case, the common gradient-based methods generally use the sign function to generate perturbations on the gradient update, that offers a roughly correct direction and has gained great success.
Rethinking the Backward Propagation for Adversarial Transferability
input image and loss function so as to generate adversarial examples with higher transferability.
Knowledge Distillation via Token-level Relationship Graph
To address the above limitations, we propose a novel method called Knowledge Distillation with Token-level Relationship Graph (TRG) that leverages the token-wise relational knowledge to enhance the performance of knowledge distillation.
Two Independent Teachers are Better Role Model
In this work, we address the above limitations by designing a new deep-learning model, called 3D-DenseUNet, which works as adaptable global aggregation blocks in down-sampling to solve the issue of spatial information loss.
Tokenized Graph Transformer with Neighborhood Augmentation for Node Classification in Large Graphs
Graph Transformers, emerging as a new architecture for graph representation learning, suffer from the quadratic complexity on the number of nodes when handling large graphs.
AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimation
To obtain high-quality 3D hand pose annotations for the egocentric images, we develop an efficient pipeline, where we use an initial set of manual annotations to train a model to automatically annotate a much larger dataset.
Meta-multigraph Search: Rethinking Meta-structure on Heterogeneous Information Networks
Meta-structures are widely used to define which subset of neighbors to aggregate information in heterogeneous information networks (HINs).
Pointerformer: Deep Reinforced Multi-Pointer Transformer for the Traveling Salesman Problem
Traveling Salesman Problem (TSP), as a classic routing optimization problem originally arising in the domain of transportation and logistics, has become a critical task in broader domains, such as manufacturing and biology.
PIAT: Parameter Interpolation based Adversarial Training for Image Classification
Besides, we suggest to use the Normalized Mean Square Error (NMSE) to further improve the robustness by aligning the clean and adversarial examples.
GMConv: Modulating Effective Receptive Fields for Convolutional Kernels
Inspired by the property that ERFs typically exhibit a Gaussian distribution, we propose a Gaussian Mask convolutional kernel (GMConv) in this work.
Semantic Adversarial Attacks on Face Recognition through Significant Attributes
The probability score method is based on training a Face Verification model for an attribute prediction task to obtain a class probability score for each attribute.
All in Tokens: Unifying Output Space of Visual Tasks via Soft Token
With these new techniques and other designs, we show that the proposed general-purpose task-solver can perform both instance segmentation and depth estimation well.
Ranked #14 on
Monocular Depth Estimation
on NYU-Depth V2
Incorporating Multi-armed Bandit with Local Search for MaxSAT
In this paper, we propose a local search algorithm for these problems, called BandHS, which applies two multi-armed bandits to guide the search directions when escaping local optima.
Differentiable Meta Multigraph Search with Partial Message Propagation on Heterogeneous Information Networks
To address these issues, we propose a novel method called Partial Message Meta Multigraph search (PMMM) to automatically optimize the neural architecture design on HINs.
Class-aware Information for Logit-based Knowledge Distillation
Knowledge distillation aims to transfer knowledge to the student model by utilizing the predictions/features of the teacher model, and feature-based distillation has recently shown its superiority over logit-based distillation.
On the Complexity of Bayesian Generalization
Specifically, at the $representational \ level$, we seek to answer how the complexity varies when a visual concept is mapped to the representation space.
Local Magnification for Data and Feature Augmentation
And further combination with our feature augmentation techniques, termed LOMA_IF&FO, can continue to strengthen the model and outperform advanced intensity transformation methods for data augmentation.
Adaptive Multi-Neighborhood Attention based Transformer for Graph Representation Learning
MNA-GT further employs an attention layer to learn the importance of different attention kernels to enable the model to adaptively capture the graph structural information for different nodes.
Neighborhood Convolutional Network: A New Paradigm of Graph Neural Networks for Node Classification
The decoupled Graph Convolutional Network (GCN), a recent development of GCN that decouples the neighborhood aggregation and feature transformation in each convolutional layer, has shown promising performance for graph representation learning.
Incorporating Pre-training Paradigm for Antibody Sequence-Structure Co-design
Specifically, we first pre-train an antibody language model based on the sequence data, then propose a one-shot way for sequence and structure generation of CDR to avoid the heavy cost and error propagation from an autoregressive manner, and finally leverage the pre-trained antibody model for the antigen-specific antibody generation model with some carefully designed modules.
Hybrid Learning with New Value Function for the Maximum Common Subgraph Problem
Branch-and-Bound (BnB) is the basis of a class of efficient algorithms for MCS, consisting in successively selecting vertices to match and pruning when it is discovered that a solution better than the best solution found so far does not exist.
Generating Pseudo-labels Adaptively for Few-shot Model-Agnostic Meta-Learning
Model-Agnostic Meta-Learning (MAML) is a famous few-shot learning method that has inspired many follow-up efforts, such as ANIL and BOIL.
Reinforced Lin-Kernighan-Helsgaun Algorithms for the Traveling Salesman Problems
LKH-3 is a powerful extension of LKH that can solve many TSP variants.
Propagation with Adaptive Mask then Training for Node Classification on Attributed Networks
However, they follow the traditional structure-aware propagation strategy of GCNs, making it hard to capture the attribute correlation of nodes and sensitive to the structure noise described by edges whose two endpoints belong to different categories.
NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphs
In this work, we observe that existing graph Transformers treat nodes as independent tokens and construct a single long sequence composed of all node tokens so as to train the Transformer model, causing it hard to scale to large graphs due to the quadratic complexity on the number of nodes for the self-attention computation.
Enhancing the Robustness, Efficiency, and Diversity of Differentiable Architecture Search
Differentiable architecture search (DARTS) has attracted much attention due to its simplicity and significant improvement in efficiency.
Sampling-based Fast Gradient Rescaling Method for Highly Transferable Adversarial Attacks
Deviation between the original gradient and the generated noises may lead to inaccurate gradient update estimation and suboptimal solutions for adversarial transferability, which is crucial for black-box attacks.
Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities
Assembly101 is a new procedural activity dataset featuring 4321 videos of people assembling and disassembling 101 "take-apart" toy vehicles.
Robust Textual Embedding against Word-level Adversarial Attacks
We attribute the vulnerability of natural language processing models to the fact that similar inputs are converted to dissimilar representations in the embedding space, leading to inconsistent outputs, and we propose a novel robust training method, termed Fast Triplet Metric Learning (FTML).
TextHacker: Learning based Hybrid Local Search Algorithm for Text Hard-label Adversarial Attack
Existing textual adversarial attacks usually utilize the gradient or prediction confidence to generate adversarial examples, making it hard to be deployed in real-world applications.
BandMaxSAT: A Local Search MaxSAT Solver with Multi-armed Bandit
We address Partial MaxSAT (PMS) and Weighted PMS (WPMS), two practical generalizations of the MaxSAT problem, and propose a local search algorithm for these problems, called BandMaxSAT, that applies a multi-armed bandit model to guide the search direction.
Rethinking the Data Annotation Process for Multi-view 3D Pose Estimation with Active Learning and Self-Training
Notably, on CMU Panoptic Studio, we are able to reduce the turn-around time by 60% and annotation cost by 80% when compared to the conventional annotation process.
Triangle Attack: A Query-efficient Decision-based Adversarial Attack
Decision-based attack poses a severe threat to real-world applications since it regards the target model as a black box and only accesses the hard prediction label.
Uncovering the Local Hidden Community Structure in Social Networks
We theoretically show that our method can avoid some situations that a broken community and the local community are regarded as one community in the subgraph, leading to the inaccuracy on detection which can be caused by global hidden community detection methods.
Stochastic Variance Reduced Ensemble Adversarial Attack for Boosting the Adversarial Transferability
The black-box adversarial attack has attracted impressive attention for its practical use in the field of deep learning security.
Tracklet-Switch Adversarial Attack against Pedestrian Multi-Object Tracking Trackers
Multi-Object Tracking (MOT) has achieved aggressive progress and derived many excellent deep learning trackers.
Stochastic Variance Reduced Ensemble Adversarial Attack
Black-box adversarial attack has attracted much attention for its practical use in deep learning applications, and it is very challenging as there is no access to the architecture and weights of the target model.
Detecting Textual Adversarial Examples through Randomized Substitution and Vote
Based on this observation, we propose a novel textual adversarial example detection method, termed Randomized Substitution and Vote (RS&V), which votes the prediction label by accumulating the logits of k samples generated by randomly substituting the words in the input text with synonyms.
TimeTraveler: Reinforcement Learning for Temporal Knowledge Graph Forecasting
Compared with the completion task, the forecasting task is more difficult that faces two main challenges: (1) how to effectively model the time information to handle future timestamps?
Regional Adversarial Training for Better Robust Generalization
Adversarial training (AT) has been demonstrated as one of the most promising defense methods against various adversarial attacks.
Farsighted Probabilistic Sampling: A General Strategy for Boosting Local Search MaxSAT Solvers
In this work, we observe that most local search (W)PMS solvers usually flip a single variable per iteration.
A New Entity Extraction Method Based on Machine Reading Comprehension
Entity extraction is a key technology for obtaining information from massive texts in natural language processing.
Crafting Adversarial Examples for Neural Machine Translation
We first show the current NMT adversarial attacks may be improperly estimated by the commonly used mono-directional translation, and we propose to leverage the round-trip translation technique to build valid metrics for evaluating NMT adversarial attacks.
Structure Amplification on Multi-layer Stochastic Block Models
Our previous work proposes a general structure amplification technique called HICODE that uncovers many layers of functional hidden structure in complex networks.
Reinforced Hybrid Genetic Algorithm for the Traveling Salesman Problem
In the hybrid algorithm, LKH can help EAX-GA improve the population by its effective local search, and EAX-GA can help LKH escape from local optima by providing high-quality and diverse initial solutions.
Integrating Large Circular Kernels into CNNs through Neural Architecture Search
We first propose a simple yet efficient implementation of the convolution using circular kernels, and empirically show the significant advantages of large circular kernels over the counterpart square kernels.
Multi-stage Optimization based Adversarial Training
In this work, we aim to avoid the catastrophic overfitting by introducing multi-step adversarial examples during the single-step adversarial training.
Enhancing the Transferability of Adversarial Attacks through Variance Tuning
Incorporating variance tuning with input transformations on iterative gradient-based attacks in the multi-model setting, the integrated method could achieve an average success rate of 90. 1% against nine advanced defense methods, improving the current best attack performance significantly by 85. 1% .
Boosting Adversarial Transferability through Enhanced Momentum
Various momentum iterative gradient-based methods are shown to be effective to improve the adversarial transferability.
Admix: Enhancing the Transferability of Adversarial Attacks
We investigate in this direction and observe that existing transformations are all applied on a single image, which might limit the adversarial transferability.
AT-GAN: An Adversarial Generative Model for Non-constrained Adversarial Examples
A recent work targets unrestricted adversarial example using generative model but their method is based on a search in the neighborhood of input noise, so actually their output is still constrained by input.
Combining Reinforcement Learning with Lin-Kernighan-Helsgaun Algorithm for the Traveling Salesman Problem
We address the Traveling Salesman Problem (TSP), a famous NP-hard combinatorial optimization problem.
Tight Lower Complexity Bounds for Strongly Convex Finite-Sum Optimization
Finite-sum optimization plays an important role in the area of machine learning, and hence has triggered a surge of interest in recent years.
Adversarial Training with Fast Gradient Projection Method against Synonym Substitution based Text Attacks
Adversarial training is the most empirically successful approach in improving the robustness of deep neural networks for image classification. For text classification, however, existing synonym substitution based adversarial attacks are effective but not efficient to be incorporated into practical text adversarial training.
Probability Learning based Tabu Search for the Budgeted Maximum Coverage Problem
As the counterpart problem of SUKP, however, BMCP was introduced early in 1999 but since then it has been rarely studied, especially there is no practical algorithm proposed.
Dynamic Graph Correlation Learning for Disease Diagnosis with Incomplete Labels
In this work, we propose a Disease Diagnosis Graph Convolutional Network (DD-GCN) that presents a novel view of investigating the inter-dependency among different diseases by using a dynamic learnable adjacency matrix in graph structure to improve the diagnosis accuracy.
Error-feedback stochastic modeling strategy for time series forecasting with convolutional neural networks
Despite the superiority of convolutional neural networks demonstrated in time series modeling and forecasting, it has not been fully explored on the design of the neural network architecture and the tuning of the hyper-parameters.
Stochastic Item Descent Method for Large Scale Equal Circle Packing Problem
Inspired by its success in deep learning, we apply the idea of SGD with batch selection of samples to a classic optimization problem in decision version.
Adaptive Large Neighborhood Search for Circle Bin Packing Problem
We address a new variant of packing problem called the circle bin packing problem (CBPP), which is to find a dense packing of circle items to multiple square bins so as to minimize the number of used bins.
Single Image Reflection Removal through Cascaded Refinement
IBCLN is a cascaded network that iteratively refines the estimates of transmission and reflection layers in a manner that they can boost the prediction quality to each other, and information across steps of the cascade is transferred using an LSTM.
Ranked #2 on
Reflection Removal
on SIR^2(Postcard)
Hierarchical hidden community detection for protein complex prediction
Results: We propose a method called HirHide (Hierarchical Hidden Community Detection), which can be combined with traditional community detection methods to enable them to discover hierarchical hidden communities.
Molecular Networks
Robust Local Features for Improving the Generalization of Adversarial Training
We continue to propose a new approach called Robust Local Features for Adversarial Training (RLFAT), which first learns the robust local features by adversarial training on the RBS-transformed adversarial examples, and then transfers the robust local features into the training of normal adversarial examples.
Natural Language Adversarial Defense through Synonym Encoding
In the area of natural language processing, deep learning models are recently known to be vulnerable to various types of adversarial perturbations, but relatively few works are done on the defense side.
Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attacks
While SIM is based on our discovery on the scale-invariant property of deep learning models, for which we leverage to optimize the adversarial perturbations over the scale copies of the input images so as to avoid "overfitting" on the white-box model being attacked and generate more transferable adversarial examples.
Generating Natural Language Adversarial Examples through Probability Weighted Word Saliency
Experiments on three popular datasets using convolutional as well as LSTM models show that PWWS reduces the classification accuracy to the most extent, and keeps a very low word substitution rate.
Adversarially Robust Generalization Just Requires More Unlabeled Data
Neural network robustness has recently been highlighted by the existence of adversarial examples.
A Learning based Branch and Bound for Maximum Common Subgraph Problems
Branch-and-bound (BnB) algorithms are widely used to solve combinatorial problems, and the performance crucially depends on its branching heuristic. In this work, we consider a typical problem of maximum common subgraph (MCS), and propose a branching heuristic inspired from reinforcement learning with a goal of reaching a tree leaf as early as possible to greatly reduce the search tree size. Extensive experiments show that our method is beneficial and outperforms current best BnB algorithm for the MCS.
A New Anchor Word Selection Method for the Separable Topic Discovery
In this work, we propose a new method for the anchor word selection by associating the word co-occurrence probability with the words similarity and assuming that the most different words on semantic are potential candidates for the anchor words.
AT-GAN: An Adversarial Generator Model for Non-constrained Adversarial Examples
In this way, AT-GAN can learn the distribution of adversarial examples that is very close to the distribution of real data.
Effective reinforcement learning based local search for the maximum k-plex problem
The maximum k-plex problem is a computationally complex problem, which emerged from graph-theoretic social network studies.
Child Gender Determination with Convolutional Neural Networks on Hand Radio-Graphs
In this work we propose a technique called GDCNN (Gender Determination with Convolutional Neural Networks), where the left hand radio-graphs of the children between a wide range of ages in 1 month to 18 years are examined to determine the gender.
Towards Understanding Learning Representations: To What Extent Do Different Neural Networks Learn the Same Representation
The theory gives a complete characterization of the structure of neuron activation subspace matches, where the core concepts are maximum match and simple match which describe the overall and the finest similarity between sets of neurons in two networks respectively.
Improving the Generalization of Adversarial Training with Domain Adaptation
Our intuition is to regard the adversarial training on FGSM adversary as a domain adaption task with limited number of target domain samples.
An Iterative Path-Breaking Approach with Mutation and Restart Strategies for the MAX-SAT Problem
Although Path-Relinking is an effective local search method for many combinatorial optimization problems, its application is not straightforward in solving the MAX-SAT, an optimization variant of the satisfiability problem (SAT) that has many real-world applications and has gained more and more attention in academy and industry.
Hashing with Binary Matrix Pursuit
We propose theoretical and empirical improvements for two-stage hashing methods.
Local Descriptors Optimized for Average Precision
In this paper, we improve the learning of local feature descriptors by optimizing the performance of descriptor matching, which is a common stage that follows descriptor extraction in local feature based pipelines, and can be formulated as nearest neighbor retrieval.
Multilevel Language and Vision Integration for Text-to-Clip Retrieval
To capture the inherent structures present in both text and video, we introduce a multilevel model that integrates vision and language features earlier and more tightly than prior work.
Hashing with Mutual Information
Binary vector embeddings enable fast nearest neighbor retrieval in large databases of high-dimensional objects, and play an important role in many practical applications, such as image and video retrieval.
Krylov Subspace Approximation for Local Community Detection
Community detection is an important information mining task in many fields including computer science, social sciences, biology and physics.
Social and Information Networks
The Local Dimension of Deep Manifold
Our results show that the dimensions of different categories are close to each other and decline quickly along the convolutional layers and fully connected layers.
Hashing as Tie-Aware Learning to Rank
Hashing, or learning binary embeddings of data, is frequently used in nearest neighbor retrieval.
Predicting Foreground Object Ambiguity and Efficiently Crowdsourcing the Segmentation(s)
We propose the ambiguity problem for the foreground object segmentation task and motivate the importance of estimating and accounting for this ambiguity when designing vision systems.
Randomness in Deconvolutional Networks for Visual Representation
Toward a deeper understanding on the inner work of deep neural networks, we investigate CNN (convolutional neural network) using DCN (deconvolutional network) and randomization technique, and gain new insights for the intrinsic property of this network architecture.
MIHash: Online Hashing with Mutual Information
Learning-based hashing methods are widely used for nearest neighbor retrieval, and recently, online hashing methods have demonstrated good performance-complexity trade-offs by learning hash functions from streaming data.
Hidden Community Detection in Social Networks
We introduce a new paradigm that is important for community detection in the realm of network analysis.
A Powerful Generative Model Using Random Weights for the Deep Image Representation
To our knowledge this is the first demonstration of image representations using untrained deep neural networks.
Uncovering the Small Community Structure in Large Networks: A Local Spectral Approach
Nowadays, as we often explore networks with billions of vertices and find communities of size hundreds, it is crucial to shift our attention from macroscopic structure to microscopic structure when dealing with large networks.
Social and Information Networks Data Structures and Algorithms Physics and Society G.2.2; H.3.3
Generalized Majorization-Minimization
Majorization-Minimization (MM) is a powerful iterative procedure for optimizing non-convex functions that works by optimizing a sequence of bounds on the function.
Revealing Multiple Layers of Hidden Community Structure in Networks
Additionally, on both real and synthetic networks containing a hidden ground-truth community structure, HICODE uncovers this structure better than any baseline algorithms that we compared against.
Social and Information Networks Physics and Society
