Search Results for author:
Found 95 papers, 26 papers with code
Revisiting the Dataset Bias Problem from a Statistical Perspective
To overcome this challenge, we propose to approximate \frac{1}{p(u|b)} using a biased classifier trained with "bias amplification" losses.
Root Cause Explanation of Outliers under Noisy Mechanisms
We then represent the functional form of a target outlier leaf as a function of the node and edge noises.
LaGR-SEQ: Language-Guided Reinforcement Learning with Sample-Efficient Querying
To address this issue, we introduce SEQ (sample efficient querying), where we simultaneously train a secondary RL agent to decide when the LLM should be queried for solutions.
Persistent-Transient Duality: A Multi-mechanism Approach for Modeling Human-Object Interaction
To bridge that gap, this work proposes to model two concurrent mechanisms that jointly control human motion: the Persistent process that runs continually on the global scale, and the Transient sub-processes that operate intermittently on the local context of the human while interacting with objects.
Memory-Augmented Theory of Mind Network
Social reasoning necessitates the capacity of theory of mind (ToM), the ability to contextualise and attribute mental states to others without having access to their internal cognitive structure.
Functional Indirection Neural Estimator for Better Out-of-distribution Generalization
FINE consists of a backbone network and a trainable semantic memory of basis weight matrices.
Momentum Adversarial Distillation: Handling Large Distribution Shifts in Data-Free Knowledge Distillation
Since the EMA generator can be considered as an ensemble of the generator's old versions and often undergoes a smaller change in updates compared to the generator, training on its synthetic samples can help the student recall the past knowledge and prevent the student from adapting too quickly to new updates of the generator.
Video Dialog as Conversation about Objects Living in Space-Time
To tackle these challenges we present a new object-centric framework for video dialog that supports neural reasoning dubbed COST - which stands for Conversation about Objects in Space-Time.
Guiding Visual Question Answering with Attention Priors
This grounding guides the attention mechanism inside VQA models through a duality of mechanisms: pre-training attention weight calculation and directly guiding the weights at inference time on a case-by-case basis.
Fast Conditional Network Compression Using Bayesian HyperNetworks
We introduce a conditional compression problem and propose a fast framework for tackling it.
Persistent-Transient Duality in Human Behavior Modeling
We propose to model the persistent-transient duality in human behavior using a parent-child multi-channel neural network, which features a parent persistent channel that manages the global dynamics and children transient channels that are initiated and terminated on-demand to handle detailed interactive actions.
Learning to Transfer Role Assignment Across Team Sizes
In particular, we train a role assignment network for small teams by demonstration and transfer the network to larger teams, which continue to learn through interaction with the environment.
Learning Theory of Mind via Dynamic Traits Attribution
Inspired by the observation that humans often infer the character traits of others, then use it to explain behaviour, we propose a new neural ToM architecture that learns to generate a latent trait vector of an actor from the past trajectories.
Towards Effective and Robust Neural Trojan Defenses via Input Filtering
Trojan attacks on deep neural networks are both dangerous and surreptitious.
Learning to Discover Medicines
Discovering new medicines is the hallmark of human endeavor to live a better and longer life.
Mitigating cold start problems in drug-target affinity prediction with interaction knowledge transferring
While the drug or target representation can be learned in an unsupervised manner, it still lacks the interaction information, which is critical in drug-target interaction.
Model-Based Episodic Memory Induces Dynamic Hybrid Controls
Episodic control enables sample efficiency in reinforcement learning by recalling past experiences from an episodic memory.
Balanced Q-learning: Combining the Influence of Optimistic and Pessimistic Targets
The optimistic nature of the Q-learning target leads to an overestimation bias, which is an inherent problem associated with standard $Q-$learning.
Reachability Traces for Curriculum Design in Reinforcement Learning
The objective in goal-based reinforcement learning is to learn a policy to reach a particular goal state within the environment.
Generative Pseudo-Inverse Memory
We propose Generative Pseudo-Inverse Memory (GPM), a class of deep generative memory models that are fast to write in and read out.
Clustering by Maximizing Mutual Information Across Views
We propose a novel framework for image clustering that incorporates joint representation learning and clustering.
Hierarchical Object-oriented Spatio-Temporal Reasoning for Video Question Answering
Toward reaching this goal we propose an object-oriented reasoning approach in that video is abstracted as a dynamic stream of interacting objects.
A Spatio-temporal Attention-based Model for Infant Movement Assessment from Videos
The absence or abnormality of fidgety movements of joints or limbs is strongly indicative of cerebral palsy in infants.
Object-Centric Representation Learning for Video Question Answering
Video question answering (Video QA) presents a powerful testbed for human-like intelligent behaviors.
Counterfactual Explanation with Multi-Agent Reinforcement Learning for Drug Target Prediction
Methods: We propose a multi-agent reinforcement learning framework, Multi-Agent Counterfactual Drug target binding Affinity (MACDA), to generate counterfactual explanations for the drug-protein complex.
Learning Asynchronous and Sparse Human-Object Interaction in Videos
Their interactions are sparse in time hence more faithful to the true underlying nature and more robust in inference and learning.
Semi-Supervised Learning with Variational Bayesian Inference and Maximum Uncertainty Regularization
We propose two generic methods for improving semi-supervised learning (SSL).
Logically Consistent Loss for Visual Question Answering
We propose a new model-agnostic logic constraint to tackle this issue by formulating a logically consistent loss in the multi-task learning framework as well as a data organisation called family-batch and hybrid-batch.
Goal-driven Long-Term Trajectory Prediction
We design Goal-driven Trajectory Prediction model - a dual-channel neural network that realizes such intuition.
Toward a Generalization Metric for Deep Generative Models
In this paper, we investigate the capacity of these metrics in measuring the generalization capacity.
Hierarchical Conditional Relation Networks for Multimodal Video Question Answering
Video QA challenges modelers in multiple fronts.
GEFA: Early Fusion Approach in Drug-Target Affinity Prediction
In addition, previous DTA methods learn protein representation solely based on a small number of protein sequences in DTA datasets while neglecting the use of proteins outside of the DTA datasets.
Unsupervised Anomaly Detection on Temporal Multiway Data
These include the capacity of the compact matrix LSTM to compress noisy data near perfectly, making the strategy of compressing-decompressing data ill-suited for anomaly detection under the noise.
Theory of Mind with Guilt Aversion Facilitates Cooperative Reinforcement Learning
In psychological game theory, guilt aversion necessitates modelling of agents that have theory about what other agents think, also known as Theory of Mind (ToM).
Learning to Abstract and Predict Human Actions
We propose Hierarchical Encoder-Refresher-Anticipator, a multi-level neural machine that can learn the structure of human activities by observing a partial hierarchy of events and roll-out such structure into a future prediction in multiple levels of abstraction.
Variational Hyper-Encoding Networks
Given a target distribution, we predict the posterior distribution of the latent code, then use a matrix-network decoder to generate a posterior distribution q(\theta).
Dynamic Language Binding in Relational Visual Reasoning
We present Language-binding Object Graph Network, the first neural reasoning method with dynamic relational structures across both visual and textual domains with applications in visual question answering.
Hierarchical Conditional Relation Networks for Video Question Answering
Video question answering (VideoQA) is challenging as it requires modeling capacity to distill dynamic visual artifacts and distant relations and to associate them with linguistic concepts.
Ranked #3 on
Audio-Visual Question Answering (AVQA)
on AVQA
Audio-Visual Question Answering (AVQA)
Question Answering
+4
Self-Attentive Associative Memory
Heretofore, neural networks with external memory are restricted to single memory with lossy representations of memory interactions.
Ranked #1 on
Question Answering
on bAbi
Learning Transferable Domain Priors for Safe Exploration in Reinforcement Learning
Prior access to domain knowledge could significantly improve the performance of a reinforcement learning agent.
Theory and Evaluation Metrics for Learning Disentangled Representations
We make two theoretical contributions to disentanglement learning by (a) defining precise semantics of disentangled representations, and (b) establishing robust metrics for evaluation.
Neural Reasoning, Fast and Slow, for Video Question Answering
While recent advances in lingual and visual question answering have enabled sophisticated representations and neural reasoning mechanisms, major challenges in Video QA remain on dynamic grounding of concepts, relations and actions to support the reasoning process.
Neural Stored-program Memory
Neural networks powered with external memory simulate computer behaviors.
Ranked #5 on
Question Answering
on bAbi
(Mean Error Rate metric)
Learning Regularity in Skeleton Trajectories for Anomaly Detection in Videos
Appearance features have been widely used in video anomaly detection even though they contain complex entangled factors.
Ranked #6 on
Video Anomaly Detection
on HR-ShanghaiTech
Improving Generalization and Stability of Generative Adversarial Networks
We propose a zero-centered gradient penalty for improving the generalization of the discriminator by pushing it toward the optimal discriminator.
Learning to Remember More with Less Memorization
Memory-augmented neural networks consisting of a neural controller and an external memory have shown potentials in long-term sequential learning.
Ranked #5 on
Text Classification
on Yahoo! Answers
Towards effective AI-powered agile project management
The rise of Artificial intelligence (AI) has the potential to significantly transform the practice of project management.
Graph Transformation Policy Network for Chemical Reaction Prediction
We address a fundamental problem in chemistry known as chemical reaction product prediction.
Relational dynamic memory networks
Neural networks excel in detecting regular patterns but are less successful in representing and manipulating complex data structures, possibly due to the lack of an external memory.
Variational Memory Encoder-Decoder
Introducing variability while maintaining coherence is a core task in learning to generate utterances in conversation.
On Catastrophic Forgetting and Mode Collapse in Generative Adversarial Networks
We show that GAN training is a continual learning problem in which the sequence of changing model distributions is the sequence of tasks to the discriminator.
Attentional Multilabel Learning over Graphs: A Message Passing Approach
GAML regards labels as auxiliary nodes and models them in conjunction with the input graph.
Dual Control Memory Augmented Neural Networks for Treatment Recommendations
The decoding controller generates a treatment sequence, one treatment option at a time.
DeepProcess: Supporting business process execution using a MANN-based recommender system
Process-aware Recommender systems can provide critical decision support functionality to aid business process execution by recommending what actions to take next.
Resset: A Recurrent Model for Sequence of Sets with Applications to Electronic Medical Records
The same hold for the bag of treatments.
A deep tree-based model for software defect prediction
Defects are common in software systems and can potentially cause various problems to software users.
Software Engineering
Dual Memory Neural Computer for Asynchronous Two-view Sequential Learning
One of the core tasks in multi-view learning is to capture relations among views.
Knowledge Graph Embedding with Multiple Relation Projections
Knowledge graphs contain rich relational structures of the world, and thus complement data-driven machine learning in heterogeneous data.
Graph Memory Networks for Molecular Activity Prediction
GraphMem is capable of jointly training on multiple datasets by using a specific-task query fed to the controller as an input.
Finding Algebraic Structure of Care in Time: A Deep Learning Approach
The interaction between diseases and treatments at a visit is modeled as the residual of the diseases minus the treatments.
Nonnegative Restricted Boltzmann Machines for Parts-based Representations Discovery and Predictive Model Stabilization
Of current representation learning schemes, restricted Boltzmann machines (RBMs) have proved to be highly effective in unsupervised settings.
Statistical Latent Space Approach for Mixed Data Modelling and Applications
The analysis of mixed data has been raising challenges in statistics and machine learning.
Graph Classification via Deep Learning with Virtual Nodes
The representation of the virtual node is then the representation of the entire graph.
Automatic feature learning for vulnerability prediction
Code flaws or vulnerabilities are prevalent in software systems and can potentially cause a variety of problems including deadlock, information loss, or system failure.
Software Engineering
Deep Learning to Attend to Risk in ICU
At the reasoning layer, evidences across time steps are weighted and combined.
Learning Deep Matrix Representations
We derive several new deep networks: (i) feed-forward nets that map an input matrix into an output matrix, (ii) recurrent nets which map a sequence of input matrices into a sequence of output matrices.
One Size Fits Many: Column Bundle for Multi-X Learning
Much recent machine learning research has been directed towards leveraging shared statistics among labels, instances and data views, commonly referred to as multi-label, multi-instance and multi-view learning.
Multilevel Anomaly Detection for Mixed Data
We propose MIXMAD, which stands for MIXed data Multilevel Anomaly Detection, an ensemble method that estimates the sparse regions across multiple levels of abstraction of mixed data.
Stabilizing Linear Prediction Models using Autoencoder
Using a linear model as basis for prediction, we achieve feature stability by regularising latent correlation in features.
Column Networks for Collective Classification
CLN has many desirable theoretical properties: (i) it encodes multi-relations between any two instances; (ii) it is deep and compact, allowing complex functions to be approximated at the network level with a small set of free parameters; (iii) local and relational features are learned simultaneously; (iv) long-range, higher-order dependencies between instances are supported naturally; and (v) crucially, learning and inference are efficient, linear in the size of the network and the number of relations.
A deep learning model for estimating story points
Although there has been substantial research in software analytics for effort estimation in traditional software projects, little work has been done for estimation in agile projects, especially estimating user stories or issues.
Outlier Detection on Mixed-Type Data: An Energy-based Approach
We evaluate the proposed method on synthetic and real-world datasets and demonstrate that (a) a proper handling mixed-types is necessary in outlier detection, and (b) free-energy of Mv. RBM is a powerful and efficient outlier scoring method, which is highly competitive against state-of-the-arts.
Faster Training of Very Deep Networks Via p-Norm Gates
Gates are employed in many recent state-of-the-art recurrent models such as LSTM and GRU, and feedforward models such as Residual Nets and Highway Networks.
A deep language model for software code
Existing language models such as n-grams for software code often fail to capture a long context where dependent code elements scatter far apart.
DeepSoft: A vision for a deep model of software
Although software analytics has experienced rapid growth as a research area, it has not yet reached its full potential for wide industrial adoption.
Preterm Birth Prediction: Deriving Stable and Interpretable Rules from High Dimensional Data
Preterm births occur at an alarming rate of 10-15%.
Deepr: A Convolutional Net for Medical Records
On top of the sequence is a convolutional neural net that detects and combines predictive local clinical motifs to stratify the risk.
An evaluation of randomized machine learning methods for redundant data: Predicting short and medium-term suicide risk from administrative records and risk assessments
Accurate prediction of suicide risk in mental health patients remains an open problem.
Learning deep representation of multityped objects and tasks
We introduce a deep multitask architecture to integrate multityped representations of multimodal objects.
Choice by Elimination via Deep Neural Networks
We introduce Neural Choice by Elimination, a new framework that integrates deep neural networks into probabilistic sequential choice models for learning to rank.
Collaborative filtering via sparse Markov random fields
Recommender systems play a central role in providing individualized access to information and services.
DeepCare: A Deep Dynamic Memory Model for Predictive Medicine
We introduce DeepCare, an end-to-end deep dynamic neural network that reads medical records, stores previous illness history, infers current illness states and predicts future medical outcomes.
MCMC for Hierarchical Semi-Markov Conditional Random Fields
In this contribution, we propose a new approximation technique that may have the potential to achieve sub-cubic time complexity in length and linear time depth, at the cost of some loss of quality.
Human Activity Learning and Segmentation using Partially Hidden Discriminative Models
Learning and understanding the typical patterns in the daily activities and routines of people from low-level sensory data is an important problem in many application domains such as building smart environments, or providing intelligent assistance.
Boosted Markov Networks for Activity Recognition
We explore a framework called boosted Markov networks to combine the learning capacity of boosting and the rich modeling semantics of Markov networks and applying the framework for video-based activity recognition.
Thurstonian Boltzmann Machines: Learning from Multiple Inequalities
We introduce Thurstonian Boltzmann Machines (TBM), a unified architecture that can naturally incorporate a wide range of data inputs at the same time.
Learning From Ordered Sets and Applications in Collaborative Ranking
Ranking over sets arise when users choose between groups of items.
Cumulative Restricted Boltzmann Machines for Ordinal Matrix Data Analysis
Ordinal data is omnipresent in almost all multiuser-generated feedback - questionnaires, preferences etc.
Learning Structured Outputs from Partial Labels using Forest Ensemble
Learning structured outputs with general structures is computationally challenging, except for tree-structured models.
Stabilizing Sparse Cox Model using Clinical Structures in Electronic Medical Records
Stability in clinical prediction models is crucial for transferability between studies, yet has received little attention.
Permutation Models for Collaborative Ranking
Focusing on the core of the collaborative ranking process, the user and their community, we propose new models for representation of the underlying permutations and prediction of ranks.
Learning Rank Functionals: An Empirical Study
In practical settings, the task often reduces to estimating a rank functional of an object with respect to a query.
Tree-based iterated local search for Markov random fields with applications in image analysis
The \emph{maximum a posteriori} (MAP) assignment for general structure Markov random fields (MRFs) is computationally intractable.
Global optimization using Lévy flights
This paper studies a class of enhanced diffusion processes in which random walkers perform L\'evy flights and apply it for global optimization.
