Search Results for author:
Found 163 papers, 74 papers with code
Learning to Navigate in Synthetically Accessible Chemical Space Using Reinforcement Learning
In this work, we propose a novel reinforcement learning (RL) setup for drug discovery that addresses this challenge by embedding the concept of synthetic accessibility directly into the de novo compound design system.
Feature-level Incongruence Reduction for Multimodal Translation
Besides of linguistic features in captions, MNMT allows visual(image) features to be used.
Few-shot Relation Extraction via Bayesian Meta-learning on Task Graphs
This paper studies few-shot relation extraction, which aims at predicting the relation for a pair of entities in a sentence by training with a few labeled examples in each relation.
A Group Symmetric Stochastic Differential Equation Model for Molecule Multi-modal Pretraining
Meanwhile, existing molecule multi-modal pretraining approaches approximate MI based on the representation space encoded from the topology and geometry, thus resulting in the loss of critical structural information of molecules.
CMG-Net: An End-to-End Contact-Based Multi-Finger Dexterous Grasping Network
Our work significantly outperforms the state-of-the-art for three-finger robotic hands.
CP$^3$: Channel Pruning Plug-in for Point-based Networks
CP$^3$ is elaborately designed to leverage the characteristics of point clouds and PNNs in order to enable 2D channel pruning methods for PNNs.
Enhancing Protein Language Models with Structure-based Encoder and Pre-training
Despite the ability to implicitly capture inter-residue contact information, transformer-based PLMs cannot encode protein structures explicitly for better structure-aware protein representations.
GraphVF: Controllable Protein-Specific 3D Molecule Generation with Variational Flow
In particular, GraphVF represents the first controllable geometry-aware, protein-specific molecule generation method, which can generate binding 3D molecules with tailored sub-structures and physio-chemical properties.
A Text-guided Protein Design Framework
Current AI-assisted protein design mainly utilizes protein sequential and structural information.
Physics-Inspired Protein Encoder Pre-Training via Siamese Sequence-Structure Diffusion Trajectory Prediction
DiffPreT guides the encoder to recover the native protein sequences and structures from the perturbed ones along the multimodal diffusion trajectory, which acquires the joint distribution of sequences and structures.
ProtST: Multi-Modality Learning of Protein Sequences and Biomedical Texts
On downstream tasks, ProtST enables both supervised learning and zero-shot prediction.
Towards Long-Term Time-Series Forecasting: Feature, Pattern, and Distribution
Long-term time-series forecasting (LTTF) has become a pressing demand in many applications, such as wind power supply planning.
ScaleKD: Distilling Scale-Aware Knowledge in Small Object Detector
Unlike existing works that struggle to balance the trade-off between inference speed and SOD performance, in this paper, we propose a novel Scale-aware Knowledge Distillation (ScaleKD), which transfers knowledge of a complex teacher model to a compact student model.
CP3: Channel Pruning Plug-In for Point-Based Networks
Directly implementing the 2D CNN channel pruning methods to PNNs undermine the performance of PNNs because of the different representations of 2D images and 3D point clouds as well as the network architecture disparity.
Multi-modal Molecule Structure-text Model for Text-based Retrieval and Editing
There is increasing adoption of artificial intelligence in drug discovery.
GAUCHE: A Library for Gaussian Processes in Chemistry
By defining such kernels in GAUCHE, we seek to open the door to powerful tools for uncertainty quantification and Bayesian optimisation in chemistry.
EurNet: Efficient Multi-Range Relational Modeling of Spatial Multi-Relational Data
We study EurNets in two important domains for image and protein structure modeling.
Flaky Performances when Pretraining on Relational Databases
We explore the downstream task performances for graph neural network (GNN) self-supervised learning (SSL) methods trained on subgraphs extracted from relational databases (RDBs).
Learning on Large-scale Text-attributed Graphs via Variational Inference
In this paper, we propose an efficient and effective solution to learning on large text-attributed graphs by fusing graph structure and language learning with a variational Expectation-Maximization (EM) framework, called GLEM.
Ranked #1 on
Node Property Prediction
on ogbn-papers100M
Protein Sequence and Structure Co-Design with Equivariant Translation
Proteins are macromolecules that perform essential functions in all living organisms.
Inductive Logical Query Answering in Knowledge Graphs
Exploring the efficiency--effectiveness trade-off, we find the inductive relational structure representation method generally achieves higher performance, while the inductive node representation method is able to answer complex queries in the inference-only regime without any training on queries and scales to graphs of millions of nodes.
E3Bind: An End-to-End Equivariant Network for Protein-Ligand Docking
In silico prediction of the ligand binding pose to a given protein target is a crucial but challenging task in drug discovery.
FusionRetro: Molecule Representation Fusion via In-Context Learning for Retrosynthetic Planning
Current strategies use a decoupled approach of single-step retrosynthesis models and search algorithms, taking only the product as the input to predict the reactants for each planning step and ignoring valuable context information along the synthetic route.
Debiasing Graph Neural Networks via Learning Disentangled Causal Substructure
However, by presenting a graph classification investigation on the training graphs with severe bias, surprisingly, we discover that GNNs always tend to explore the spurious correlations to make decision, even if the causal correlation always exists.
Label-Guided Auxiliary Training Improves 3D Object Detector
Detecting 3D objects from point clouds is a practical yet challenging task that has attracted increasing attention recently.
Continual Few-Shot Learning with Adversarial Class Storage
In this paper, we define a new problem called continual few-shot learning, in which tasks arrive sequentially and each task is associated with a few training samples.
Molecular Geometry Pretraining with SE(3)-Invariant Denoising Distance Matching
Further by leveraging an SE(3)-invariant score matching method, we propose GeoSSL-DDM in which the coordinate denoising proxy task is effectively boiled down to denoising the pairwise atomic distances in a molecule.
Evaluating Self-Supervised Learning for Molecular Graph Embeddings
Graph Self-Supervised Learning (GSSL) paves the way for learning graph embeddings without expert annotation, which is particularly impactful for molecular graphs since the number of possible molecules is enormous and labels are expensive to obtain.
A*Net: A Scalable Path-based Reasoning Approach for Knowledge Graphs
Experiments on both transductive and inductive knowledge graph reasoning benchmarks show that A*Net achieves competitive performance with existing state-of-the-art path-based methods, while merely visiting 10% nodes and 10% edges at each iteration.
Ranked #8 on
Link Property Prediction
on ogbl-wikikg2
PEER: A Comprehensive and Multi-Task Benchmark for Protein Sequence Understanding
However, there is a lack of a standard benchmark to evaluate the performance of different methods, which hinders the progress of deep learning in this field.
Retrieval-enhanced Graph Neural Networks for Graph Property Prediction
In GraphRetrieval, similar training graphs associated with their ground-truth labels are retrieved as an enhancement to be jointly utilized with the input graph representation to complete various graph property predictive tasks.
HIRL: A General Framework for Hierarchical Image Representation Learning
This framework aims to learn multiple semantic representations for each image, and these representations are structured to encode image semantics from fine-grained to coarse-grained.
High-Order Pooling for Graph Neural Networks with Tensor Decomposition
Graph Neural Networks (GNNs) are attracting growing attention due to their effectiveness and flexibility in modeling a variety of graph-structured data.
Tyger: Task-Type-Generic Active Learning for Molecular Property Prediction
However, existing best deep AL methods are mostly developed for a single type of learning task (e. g., single-label classification), and hence may not perform well in molecular property prediction that involves various task types.
Neural-Symbolic Models for Logical Queries on Knowledge Graphs
Answering complex first-order logic (FOL) queries on knowledge graphs is a fundamental task for multi-hop reasoning.
Neural Structured Prediction for Inductive Node Classification
This problem has been extensively studied with graph neural networks (GNNs) by learning effective node representations, as well as traditional structured prediction methods for modeling the structured output of node labels, e. g., conditional random fields (CRFs).
Weakly-supervised Temporal Path Representation Learning with Contrastive Curriculum Learning -- Extended Version
In this setting, it is essential to learn generic temporal path representations(TPRs) that consider spatial and temporal correlations simultaneously and that can be used in different applications, i. e., downstream tasks.
A Roadmap for Big Model
With the rapid development of deep learning, training Big Models (BMs) for multiple downstream tasks becomes a popular paradigm.
RGB-Depth Fusion GAN for Indoor Depth Completion
In this paper, we design a novel two-branch end-to-end fusion network, which takes a pair of RGB and incomplete depth images as input to predict a dense and completed depth map.
Protein Representation Learning by Geometric Structure Pretraining
Despite the effectiveness of sequence-based approaches, the power of pretraining on known protein structures, which are available in smaller numbers only, has not been explored for protein property prediction, though protein structures are known to be determinants of protein function.
GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation
GeoDiff treats each atom as a particle and learns to directly reverse the diffusion process (i. e., transforming from a noise distribution to stable conformations) as a Markov chain.
Subgraph Retrieval Enhanced Model for Multi-hop Knowledge Base Question Answering
Recent works on knowledge base question answering (KBQA) retrieve subgraphs for easier reasoning.
Structured Multi-task Learning for Molecular Property Prediction
However, in contrast to other domains, the performance of multi-task learning in drug discovery is still not satisfying as the number of labeled data for each task is too limited, which calls for additional data to complement the data scarcity.
CADRE: A Cascade Deep Reinforcement Learning Framework for Vision-based Autonomous Urban Driving
Vision-based autonomous urban driving in dense traffic is quite challenging due to the complicated urban environment and the dynamics of the driving behaviors.
TorchDrug: A Powerful and Flexible Machine Learning Platform for Drug Discovery
However, lacking domain knowledge (e. g., which tasks to work on), standard benchmarks and data preprocessing pipelines are the main obstacles for machine learning researchers to work in this domain.
Generative Coarse-Graining of Molecular Conformations
Coarse-graining (CG) of molecular simulations simplifies the particle representation by grouping selected atoms into pseudo-beads and drastically accelerates simulation.
LegoDNN: Block-grained Scaling of Deep Neural Networks for Mobile Vision
The prior art sheds light on exploring the accuracy-resource tradeoff by scaling the model sizes in accordance to resource dynamics.
Implications of Topological Imbalance for Representation Learning on Biomedical Knowledge Graphs
We provide support for this observation across different datasets, models as well as predictive tasks.
Make A Long Image Short: Adaptive Token Length for Vision Transformers
The TLA enables the ReViT to process the image with the minimum sufficient number of tokens during inference.
Predicting Molecular Conformation via Dynamic Graph Score Matching
However, these non-bonded atoms may be proximal to each other in 3D space, and modeling their interactions is of crucial importance to accurately determine molecular conformations, especially for large molecules and multi-molecular complexes.
Training BatchNorm Only in Neural Architecture Search and Beyond
Critically, there is no effort to understand 1) why training BatchNorm only can find the perform-well architectures with the reduced supernet-training time, and 2) what is the difference between the train-BN-only supernet and the standard-train supernet.
Joint Modeling of Visual Objects and Relations for Scene Graph Generation
We further propose an efficient and effective algorithm for inference based on mean-field variational inference, in which we first provide a warm initialization by independently predicting the objects and their relations according to the current model, followed by a few iterations of relational reasoning.
How to transfer algorithmic reasoning knowledge to learn new algorithms?
Due to the fundamental differences between algorithmic reasoning knowledge and feature extractors such as used in Computer Vision or NLP, we hypothesise that standard transfer techniques will not be sufficient to achieve systematic generalisation.
CATRO: Channel Pruning via Class-Aware Trace Ratio Optimization
Deep convolutional neural networks are shown to be overkill with high parametric and computational redundancy in many application scenarios, and an increasing number of works have explored model pruning to obtain lightweight and efficient networks.
Neural Algorithmic Reasoners are Implicit Planners
We find that prior approaches either assume that the environment is provided in such a tabular form -- which is highly restrictive -- or infer "local neighbourhoods" of states to run value iteration over -- for which we discover an algorithmic bottleneck effect.
Pre-training Molecular Graph Representation with 3D Geometry
However, the lack of 3D information in real-world scenarios has significantly impeded the learning of geometric graph representation.
Multi-task Learning with Domain Knowledge for Molecular Property Prediction
In this paper, we study multi-task learning for molecule property prediction in a different setting, where a relation graph between different tasks is available.
Human Pose Transfer with Augmented Disentangled Feature Consistency
Deep generative models have made great progress in synthesizing images with arbitrary human poses and transferring poses of one person to others.
Unsupervised Path Representation Learning with Curriculum Negative Sampling
In the global view, PIM distinguishes the representations of the input paths from those of the negative paths.
Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction
To further improve the capacity of the path formulation, we propose the Neural Bellman-Ford Network (NBFNet), a general graph neural network framework that solves the path formulation with learned operators in the generalized Bellman-Ford algorithm.
Non-Autoregressive Electron Redistribution Modeling for Reaction Prediction
Reliably predicting the products of chemical reactions presents a fundamental challenge in synthetic chemistry.
Self-supervised Graph-level Representation Learning with Local and Global Structure
This paper studies unsupervised/self-supervised whole-graph representation learning, which is critical in many tasks such as molecule properties prediction in drug and material discovery.
An End-to-End Framework for Molecular Conformation Generation via Bilevel Programming
Specifically, the molecular graph is first encoded in a latent space, and then the 3D structures are generated by solving a principled bilevel optimization program.
Learning Gradient Fields for Molecular Conformation Generation
We study a fundamental problem in computational chemistry known as molecular conformation generation, trying to predict stable 3D structures from 2D molecular graphs.
Learning Neural Generative Dynamics for Molecular Conformation Generation
Inspired by the recent progress in deep generative models, in this paper, we propose a novel probabilistic framework to generate valid and diverse conformations given a molecular graph.
Lottery Ticket Preserves Weight Correlation: Is It Desirable or Not?
In deep model compression, the recent finding "Lottery Ticket Hypothesis" (LTH) (Frankle & Carbin, 2018) pointed out that there could exist a winning ticket (i. e., a properly pruned sub-network together with original weight initialization) that can achieve competitive performance than the original dense network.
GraphSAD: Learning Graph Representations with Structure-Attribute Disentanglement
We propose to disentangle graph structure and node attributes into two distinct sets of representations, and such disentanglement can be done in either the input or the embedding space.
Decoupled Greedy Learning of Graph Neural Networks
We empirically analyse our proposed DGL-GNN model, and demonstrate its effectiveness and superior efficiency through a range of experiments.
Hierarchical Graph Attention Network for Few-Shot Visual-Semantic Learning
Deep learning has made tremendous success in computer vision, natural language processing and even visual-semantic learning, which requires a huge amount of labeled training data.
Non-autoregressive electron flow generation for reaction prediction
Our model achieves both an order of magnitude lower inference latency, with state-of-the-art top-1 accuracy and comparable performance on Top-K sampling.
Utilising Graph Machine Learning within Drug Discovery and Development
Graph Machine Learning (GML) is receiving growing interest within the pharmaceutical and biotechnology industries for its ability to model biomolecular structures, the functional relationships between them, and integrate multi-omic datasets - amongst other data types.
Towards Generalized Implementation of Wasserstein Distance in GANs
Wasserstein GANs (WGANs), built upon the Kantorovich-Rubinstein (KR) duality of Wasserstein distance, is one of the most theoretically sound GAN models.
Fast Object Detection with Latticed Multi-Scale Feature Fusion
In this work, we present a novel module, the Fluff block, to alleviate drawbacks of current multi-scale fusion methods and facilitate multi-scale object detection.
Robust Unsupervised Video Anomaly Detection by Multi-Path Frame Prediction
In this paper, we propose a novel and robust unsupervised video anomaly detection method by frame prediction with proper design which is more in line with the characteristics of surveillance videos.
DAIS: Automatic Channel Pruning via Differentiable Annealing Indicator Search
The convolutional neural network has achieved great success in fulfilling computer vision tasks despite large computation overhead against efficient deployment.
COVI-AgentSim: an Agent-based Model for Evaluating Methods of Digital Contact Tracing
The rapid global spread of COVID-19 has led to an unprecedented demand for effective methods to mitigate the spread of the disease, and various digital contact tracing (DCT) methods have emerged as a component of the solution.
$P^2$ Net: Augmented Parallel-Pyramid Net for Attention Guided Pose Estimation
We propose a refinement stage for the pyramid features to further boost the accuracy of our network.
XLVIN: eXecuted Latent Value Iteration Nets
Value Iteration Networks (VINs) have emerged as a popular method to incorporate planning algorithms within deep reinforcement learning, enabling performance improvements on tasks requiring long-range reasoning and understanding of environment dynamics.
Towards Interpretable Natural Language Understanding with Explanations as Latent Variables
In this paper, we develop a general framework for interpretable natural language understanding that requires only a small set of human annotated explanations for training.
Iterative Graph Self-Distillation
Recently, there has been increasing interest in the challenge of how to discriminatively vectorize graphs.
Predicting Infectiousness for Proactive Contact Tracing
Predictions are used to provide personalized recommendations to the individual via an app, as well as to send anonymized messages to the individual's contacts, who use this information to better predict their own infectiousness, an approach we call proactive contact tracing (PCT).
Knowledge Transfer in Multi-Task Deep Reinforcement Learning for Continuous Control
While Deep Reinforcement Learning (DRL) has emerged as a promising approach to many complex tasks, it remains challenging to train a single DRL agent that is capable of undertaking multiple different continuous control tasks.
Emergence of Chern insulating states in non-Magic angle twisted bilayer graphene
For {\theta}=1. 25{\deg}, we observe an emergence of topological insulating states at hole side with a sequence of Chern number |C|=4-|v|, where v is the number of electrons (holes) in moir\'e unite cell.
Mesoscale and Nanoscale Physics Materials Science
RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphs
Then in the E-step, we select a set of high-quality rules from all generated rules with both the rule generator and reasoning predictor via posterior inference; and in the M-step, the rule generator is updated with the rules selected in the E-step.
Graph neural induction of value iteration
Previously, such planning components have been incorporated through a neural network that partially aligns with the computational graph of value iteration.
Differentiable Feature Aggregation Search for Knowledge Distillation
To tackle with both the efficiency and the effectiveness of knowledge distillation, we introduce the feature aggregation to imitate the multi-teacher distillation in the single-teacher distillation framework by extracting informative supervision from multiple teacher feature maps.
GRADE: Graph Dynamic Embedding
At each time step link generation is performed by first assigning node membership from a distribution over the communities, and then sampling a neighbor from a distribution over the nodes for the assigned community.
Few-shot Relation Extraction via Bayesian Meta-learning on Relation Graphs
To more effectively generalize to new relations, in this paper we study the relationships between different relations and propose to leverage a global relation graph.
An Advert Creation System for 3D Product Placements
Over the past decade, the evolution of video-sharing platforms has attracted a significant amount of investments on contextual advertising.
Graph Policy Network for Transferable Active Learning on Graphs
Graph neural networks (GNNs) have been attracting increasing popularity due to their simplicity and effectiveness in a variety of fields.
COVI White Paper
Manual contact tracing of Covid-19 cases has significant challenges that limit the ability of public health authorities to minimize community infections.
Domain Conditioned Adaptation Network
Most existing deep DA models only focus on aligning feature representations of task-specific layers across domains while integrating a totally shared convolutional architecture for source and target.
Investigating Class-level Difficulty Factors in Multi-label Classification Problems
This work investigates the use of class-level difficulty factors in multi-label classification problems for the first time.
Learning To Navigate The Synthetically Accessible Chemical Space Using Reinforcement Learning
Over the last decade, there has been significant progress in the field of machine learning for de novo drug design, particularly in deep generative models.
A Graph to Graphs Framework for Retrosynthesis Prediction
A fundamental problem in computational chemistry is to find a set of reactants to synthesize a target molecule, a. k. a.
Ranked #13 on
Single-step retrosynthesis
on USPTO-50k
Learning Dynamic Belief Graphs to Generalize on Text-Based Games
Playing text-based games requires skills in processing natural language and sequential decision making.
GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generation
Molecular graph generation is a fundamental problem for drug discovery and has been attracting growing attention.
Ranked #1 on
Molecular Graph Generation
on MOSES
BLK-REW: A Unified Block-based DNN Pruning Framework using Reweighted Regularization Method
Accelerating DNN execution on various resource-limited computing platforms has been a long-standing problem.
An Image Enhancing Pattern-based Sparsity for Real-time Inference on Mobile Devices
Weight pruning has been widely acknowledged as a straightforward and effective method to eliminate redundancy in Deep Neural Networks (DNN), thereby achieving acceleration on various platforms.
Continuous Graph Neural Networks
The key idea is how to characterise the continuous dynamics of node representations, i. e. the derivatives of node representations, w. r. t.
KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation
Pre-trained language representation models (PLMs) cannot well capture factual knowledge from text.
Deep geometric knowledge distillation with graphs
Specifically we introduce a graph-based RKD method, in which graphs are used to capture the geometry of latent spaces.
Identifying Candidate Spaces for Advert Implantation
Virtual advertising is an important and promising feature in the area of online advertising.
Empowering Graph Representation Learning with Paired Training and Graph Co-Attention
Through many recent advances in graph representation learning, performance achieved on tasks involving graph-structured data has substantially increased in recent years---mostly on tasks involving node-level predictions.
Transfer Active Learning For Graph Neural Networks
Moreover, we also studied how to learn a universal policy for labeling nodes on graphs with multiple training graphs and then transfer the learned policy to unseen graphs.
GraphMix: Improved Training of GNNs for Semi-Supervised Learning
We present GraphMix, a regularization method for Graph Neural Network based semi-supervised object classification, whereby we propose to train a fully-connected network jointly with the graph neural network via parameter sharing and interpolation-based regularization.
Ranked #1 on
Node Classification
on Bitcoin-Alpha
GraphMix: Regularized Training of Graph Neural Networks for Semi-Supervised Learning
We present GraphMix, a regularization technique for Graph Neural Network based semi-supervised object classification, leveraging the recent advances in the regularization of classical deep neural networks.
Structural Robustness for Deep Learning Architectures
Deep Networks have been shown to provide state-of-the-art performance in many machine learning challenges.
PCONV: The Missing but Desirable Sparsity in DNN Weight Pruning for Real-time Execution on Mobile Devices
Model compression techniques on Deep Neural Network (DNN) have been widely acknowledged as an effective way to achieve acceleration on a variety of platforms, and DNN weight pruning is a straightforward and effective method.
Data-Driven Approach to Encoding and Decoding 3-D Crystal Structures
We present a method to encode and decode the position of atoms in 3-D molecules from a dataset of nearly 50, 000 stable crystal unit cells that vary from containing 1 to over 100 atoms.
An End-to-End Neighborhood-based Interaction Model for Knowledge-enhanced Recommendation
This paper studies graph-based recommendation, where an interaction graph is constructed from historical records and is lever-aged to alleviate data sparsity and cold start problems.
Ranked #1 on
Click-Through Rate Prediction
on MovieLens 1M
InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization
There are also some recent methods based on language models (e. g. graph2vec) but they tend to only consider certain substructures (e. g. subtrees) as graph representatives.
Ranked #21 on
Graph Classification
on IMDb-B
Weakly-supervised Knowledge Graph Alignment with Adversarial Learning
Therefore, in this paper we propose to study aligning knowledge graphs in fully-unsupervised or weakly-supervised fashion, i. e., without or with only a few aligned triplets.
AutoCompress: An Automatic DNN Structured Pruning Framework for Ultra-High Compression Rates
This work proposes AutoCompress, an automatic structured pruning framework with the following key performance improvements: (i) effectively incorporate the combination of structured pruning schemes in the automatic process; (ii) adopt the state-of-art ADMM-based structured weight pruning as the core algorithm, and propose an innovative additional purification step for further weight reduction without accuracy loss; and (iii) develop effective heuristic search method enhanced by experience-based guided search, replacing the prior deep reinforcement learning technique which has underlying incompatibility with the target pruning problem.
Ekar: An Explainable Method for Knowledge Aware Recommendation
Recently, a variety of methods have been developed for this problem, which generally try to learn effective representations of users and items and then match items to users according to their representations.
Ranked #1 on
Recommendation Systems
on Last.FM
Probabilistic Logic Neural Networks for Reasoning
In the E-step, a knowledge graph embedding model is used for inferring the missing triplets, while in the M-step, the weights of logic rules are updated based on both the observed and predicted triplets.
vGraph: A Generative Model for Joint Community Detection and Node Representation Learning
Experimental results on multiple real-world graphs show that vGraph is very effective in both community detection and node representation learning, outperforming many competitive baselines in both tasks.
Learning Powerful Policies by Using Consistent Dynamics Model
There is enough evidence that humans build a model of the environment, not only by observing the environment but also by interacting with the environment.
DivGraphPointer: A Graph Pointer Network for Extracting Diverse Keyphrases
Furthermore, we propose a diversified point network to generate a set of diverse keyphrases out of the word graph in the decoding process.
GMNN: Graph Markov Neural Networks
Statistical relational learning methods can effectively model the dependency of object labels through conditional random fields for collective classification, whereas graph neural networks learn effective object representations for classification through end-to-end training.
Localizing Adverts in Outdoor Scenes
Such techniques involve replacing an existing advertisement in a video frame, with a new advertisement.
Drug-Drug Adverse Effect Prediction with Graph Co-Attention
Complex or co-existing diseases are commonly treated using drug combinations, which can lead to higher risk of adverse side effects.
Introducing Graph Smoothness Loss for Training Deep Learning Architectures
We introduce a novel loss function for training deep learning architectures to perform classification.
Softmax Optimizations for Intel Xeon Processor-based Platforms
Softmax is popular normalization method used in machine learning.
The ALOS Dataset for Advert Localization in Outdoor Scenes
The rapid increase in the number of online videos provides the marketing and advertising agents ample opportunities to reach out to their audience.
Signal-to-Noise Ratio: A Robust Distance Metric for Deep Metric Learning
In this paper, different from the approaches on learning the loss structures, we propose a robust SNR distance metric based on Signal-to-Noise Ratio (SNR) for measuring the similarity of image pairs for deep metric learning.
Progressive DNN Compression: A Key to Achieve Ultra-High Weight Pruning and Quantization Rates using ADMM
A recent work developed a systematic frame-work of DNN weight pruning using the advanced optimization technique ADMM (Alternating Direction Methods of Multipliers), achieving one of state-of-art in weight pruning results.
The CASE Dataset of Candidate Spaces for Advert Implantation
With the advent of faster internet services and growth of multimedia content, we observe a massive growth in the number of online videos.
Learning Hierarchical Representations of Electronic Health Records for Clinical Outcome Prediction
Our model learns hierarchical representationsof event sequences, to adaptively distinguish between short-range and long-range events, and accurately capture coretemporal dependencies.
GraphVite: A High-Performance CPU-GPU Hybrid System for Node Embedding
In this paper, we propose GraphVite, a high-performance CPU-GPU hybrid system for training node embeddings, by co-optimizing the algorithm and the system.
Ranked #1 on
Node Classification
on YouTube
RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
We study the problem of learning representations of entities and relations in knowledge graphs for predicting missing links.
Ranked #2 on
Link Prediction
on FB122
Session-based Social Recommendation via Dynamic Graph Attention Networks
However, recommendation in online communities is a challenging problem: 1) users' interests are dynamic, and 2) users are influenced by their friends.
Ranked #1 on
Recommendation Systems
on Douban
(NDCG metric)
Contextualized Non-local Neural Networks for Sequence Learning
Recently, a large number of neural mechanisms and models have been proposed for sequence learning, of which self-attention, as exemplified by the Transformer model, and graph neural networks (GNNs) have attracted much attention.
ADNet: A Deep Network for Detecting Adverts
Online video advertising gives content providers the ability to deliver compelling content, reach a growing audience, and generate additional revenue from online media.
Data Poisoning Attack against Unsupervised Node Embedding Methods
In this paper, we take the task of link prediction as an example, which is one of the most fundamental problems for graph analysis, and introduce a data positioning attack to node embedding methods.
AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks
Afterwards, a multi-head self-attentive neural network with residual connections is proposed to explicitly model the feature interactions in the low-dimensional space.
Ranked #1 on
Click-Through Rate Prediction
on KDD12
Progressive Weight Pruning of Deep Neural Networks using ADMM
Motivated by dynamic programming, the proposed method reaches extremely high pruning rate by using partial prunings with moderate pruning rates.
Learning powerful policies and better dynamics models by encouraging consistency
Analogously, we would expect such interaction to be helpful for a learning agent while learning to model the environment dynamics.
StructADMM: A Systematic, High-Efficiency Framework of Structured Weight Pruning for DNNs
Without loss of accuracy on the AlexNet model, we achieve 2. 58X and 3. 65X average measured speedup on two GPUs, clearly outperforming the prior work.
DeepInf: Social Influence Prediction with Deep Learning
Inspired by the recent success of deep neural networks in a wide range of computing applications, we design an end-to-end framework, DeepInf, to learn users' latent feature representation for predicting social influence.
Adversarial Meta-Learning
Meta-learning enables a model to learn from very limited data to undertake a new task.
A Systematic DNN Weight Pruning Framework using Alternating Direction Method of Multipliers
We first formulate the weight pruning problem of DNNs as a nonconvex optimization problem with combinatorial constraints specifying the sparsity requirements, and then adopt the ADMM framework for systematic weight pruning.
On the Universal Approximation Property and Equivalence of Stochastic Computing-based Neural Networks and Binary Neural Networks
Based on the universal approximation property, we further prove that SCNNs and BNNs exhibit the same energy complexity.
Learning the Joint Representation of Heterogeneous Temporal Events for Clinical Endpoint Prediction
One important application is clinical endpoint prediction, which aims to predict whether a disease, a symptom or an abnormal lab test will happen in the future according to patients' history records.
Model-Free Control for Distributed Stream Data Processing using Deep Reinforcement Learning
Specifically, we, for the first time, propose to leverage emerging Deep Reinforcement Learning (DRL) for enabling model-free control in DSDPSs; and present design, implementation and evaluation of a novel and highly effective DRL-based control framework, which minimizes average end-to-end tuple processing time by jointly learning the system environment via collecting very limited runtime statistics data and making decisions under the guidance of powerful Deep Neural Networks.
Towards Ultra-High Performance and Energy Efficiency of Deep Learning Systems: An Algorithm-Hardware Co-Optimization Framework
Hardware accelerations of deep learning systems have been extensively investigated in industry and academia.
Deep Reinforcement Learning for Dynamic Treatment Regimes on Medical Registry Data
This paper presents the first deep reinforcement learning (DRL) framework to estimate the optimal Dynamic Treatment Regimes from observational medical data.
Experience-driven Networking: A Deep Reinforcement Learning based Approach
Modern communication networks have become very complicated and highly dynamic, which makes them hard to model, predict and control.
A Systematic Analysis for State-of-the-Art 3D Lung Nodule Proposals Generation
Lung nodule proposals generation is the primary step of lung nodule detection and has received much attention in recent years .
Adversarial Network Embedding
Learning low-dimensional representations of networks has proved effective in a variety of tasks such as node classification, link prediction and network visualization.
An Attention-based Collaboration Framework for Multi-View Network Representation Learning
Existing approaches usually study networks with a single type of proximity between nodes, which defines a single view of a network.
End-to-end Learning for Short Text Expansion
A novel deep memory network is proposed to automatically find relevant information from a collection of longer documents and reformulate the short text through a gating mechanism.
CirCNN: Accelerating and Compressing Deep Neural Networks Using Block-CirculantWeight Matrices
As the size of DNNs continues to grow, it is critical to improve the energy efficiency and performance while maintaining accuracy.
A Hierarchical Framework of Cloud Resource Allocation and Power Management Using Deep Reinforcement Learning
Automatic decision-making approaches, such as reinforcement learning (RL), have been applied to (partially) solve the resource allocation problem adaptively in the cloud computing system.