Search Results for author:
Found 71 papers, 21 papers with code
Modelling infectious disease transmission dynamics in conference environments: An individual-based approach
The global public health landscape is perpetually challenged by the looming threat of infectious diseases.
Toward a Better Understanding of Fourier Neural Operators: Analysis and Improvement from a Spectral Perspective
In solving partial differential equations (PDEs), Fourier Neural Operators (FNOs) have exhibited notable effectiveness compared to Convolutional Neural Networks (CNNs).
ICE-SEARCH: A Language Model-Driven Feature Selection Approach
This study unveils the In-Context Evolutionary Search (ICE-SEARCH) method, the first work that melds language models (LMs) with evolutionary algorithms for feature selection (FS) tasks and demonstrates its effectiveness in Medical Predictive Analytics (MPA) applications.
Structured Entity Extraction Using Large Language Models
Recent advances in machine learning have significantly impacted the field of information extraction, with Large Language Models (LLMs) playing a pivotal role in extracting structured information from unstructured text.
Improving Natural Language Understanding with Computation-Efficient Retrieval Representation Fusion
Retrieval-based augmentations that aim to incorporate knowledge from an external database into language models have achieved great success in various knowledge-intensive (KI) tasks, such as question-answering and text generation.
Natural Language Understanding
Neural Architecture Search
+5
Dual-space Hierarchical Learning for Goal-guided Conversational Recommendation
In this paper, we propose Dual-space Hierarchical Learning (DHL) to leverage multi-level goal sequences and their hierarchical relationships for conversational recommendation.
Less or More From Teacher: Exploiting Trilateral Geometry For Knowledge Distillation
A simple neural network then learns the implicit mapping from the intra- and inter-sample relations to an adaptive, sample-wise knowledge fusion ratio in a bilevel-optimization manner.
Anomaly Detection for Scalable Task Grouping in Reinforcement Learning-based RAN Optimization
This coincides with a rapid increase in the number of cell sites worldwide, driven largely by dramatic growth in cellular network traffic.
Towards Automated Negative Sampling in Implicit Recommendation
Hence, we propose a hypothesis that the negative sampler should align with the capacity of the recommendation models as well as the statistics of the datasets to achieve optimal performance.
Density-based User Representation using Gaussian Process Regression for Multi-interest Personalized Retrieval
Accurate modeling of the diverse and dynamic interests of users remains a significant challenge in the design of personalized recommender systems.
Towards Hybrid-grained Feature Interaction Selection for Deep Sparse Network
In this work, we introduce a hybrid-grained feature interaction selection approach that targets both feature field and feature value for deep sparse networks.
Adaptive Dynamic Programming for Energy-Efficient Base Station Cell Switching
In this work, we propose an approximate dynamic programming (ADP)-based method coupled with online optimization to switch on/off the cells of base stations to reduce network power consumption while maintaining adequate Quality of Service (QoS) metrics.
Teacher-Student Architecture for Knowledge Distillation: A Survey
Recently, Teacher-Student architectures have been effectively and widely embraced on various knowledge distillation (KD) objectives, including knowledge compression, knowledge expansion, knowledge adaptation, and knowledge enhancement.
Fourier neural operator for real-time simulation of 3D dynamic urban microclimate
We further evaluate the trained FNO model on unseen data with different wind directions, and the results show that the FNO model can generalize well on different wind directions.
An Evolution Kernel Method for Graph Classification through Heat Diffusion Dynamics
This approach incorporates the physics-based heat kernel and DropNode technique to transform each static graph into a sequence of temporal ones.
Think Before You Act: Decision Transformers with Internal Working Memory
We argue that this inefficiency stems from the forgetting phenomenon, in which a model memorizes its behaviors in parameters throughout training.
Policy Reuse for Communication Load Balancing in Unseen Traffic Scenarios
When deploying to an unknown traffic scenario, we select a policy from the policy bank based on the similarity between the previous-day traffic of the current scenario and the traffic observed during training.
Multi-agent Attention Actor-Critic Algorithm for Load Balancing in Cellular Networks
In cellular networks, User Equipment (UE) handoff from one Base Station (BS) to another, giving rise to the load balancing problem among the BSs.
Towards Improved Illicit Node Detection with Positive-Unlabelled Learning
Detecting illicit nodes on blockchain networks is a valuable task for strengthening future regulation.
Ternary Quantization: A Survey
Numerous research efforts have been made to compress neural network models with faster inference and higher accuracy.
Feature Representation Learning for Click-through Rate Prediction: A Review and New Perspectives
Representation learning has been a critical topic in machine learning.
Self-Supervised Transformer Architecture for Change Detection in Radio Access Networks
Such networks undergo frequent and often heterogeneous changes caused by network operators, who are seeking to tune their system parameters for optimal performance.
Optimizing Feature Set for Click-Through Rate Prediction
Because of the large-scale search space, we develop a learning-by-continuation training scheme to learn such gates.
Ranked #3 on
Click-Through Rate Prediction
on KDD12
Result Diversification in Search and Recommendation: A Survey
Diversifying return results is an important research topic in retrieval systems in order to satisfy both the various interests of customers and the equal market exposure of providers.
Hyperspherical Loss-Aware Ternary Quantization
Most of the existing works use projection functions for ternary quantization in discrete space.
Pruning On-the-Fly: A Recoverable Pruning Method without Fine-tuning
Most existing pruning works are resource-intensive, requiring retraining or fine-tuning of the pruned models for accuracy.
Hyperspherical Quantization: Toward Smaller and More Accurate Models
Model quantization enables the deployment of deep neural networks under resource-constrained devices.
Iterative Data Refinement for Self-Supervised MR Image Reconstruction
Then, we design an effective self-supervised training data refinement method to reduce this data bias.
AICOM-MP: an AI-based Monkeypox Detector for Resource-Constrained Environments
Also, through the AICOM-MP project, we have generalized a methodology of developing health AI technologies for AMCs to allow universal access even in resource-constrained environments.
Intent-aware Multi-source Contrastive Alignment for Tag-enhanced Recommendation
To offer accurate and diverse recommendation services, recent methods use auxiliary information to foster the learning process of user and item representations.
Teacher-Student Architecture for Knowledge Learning: A Survey
To tackle this issue, Teacher-Student architectures were first utilized in knowledge distillation, where simple student networks can achieve comparable performance to deep teacher networks.
Metric Distribution to Vector: Constructing Data Representation via Broad-Scale Discrepancies
Graph embedding provides a feasible methodology to conduct pattern classification for graph-structured data by mapping each data into the vectorial space.
OptEmbed: Learning Optimal Embedding Table for Click-through Rate Prediction
To this end, we propose an optimal embedding table learning framework OptEmbed, which provides a practical and general method to find an optimal embedding table for various base CTR models.
Ranked #2 on
Click-Through Rate Prediction
on KDD12
Adapting Triplet Importance of Implicit Feedback for Personalized Recommendation
In order to effectively utilize such information, most research adopts the pairwise ranking method on constructed training triplets (user, positive item, negative item) and aims to distinguish between positive items and negative items for each user.
Gradient-based Bi-level Optimization for Deep Learning: A Survey
In this survey, we first give a formal definition of the gradient-based bi-level optimization.
Confidence-Guided Unsupervised Domain Adaptation for Cerebellum Segmentation
To dispense with the manual annotation requirement, we propose to train a model to adaptively transfer the annotation from the cerebellum on the Allen Brain Human Brain Atlas to the BigBrain in an unsupervised manner, taking into account the different staining and spacing between sections.
Unbiased Implicit Feedback via Bi-level Optimization
Recent works reveal a huge gap between the implicit feedback and user-item relevance due to the fact that implicit feedback is also closely related to the item exposure.
Joint Multisided Exposure Fairness for Recommendation
Prior research on exposure fairness in the context of recommender systems has focused mostly on disparities in the exposure of individual or groups of items to individual users of the system.
Structure-aware Protein Self-supervised Learning
Furthermore, we propose to leverage the available protein language model pretrained on protein sequences to enhance the self-supervised learning.
Encoder-Decoder Architecture for Supervised Dynamic Graph Learning: A Survey
However, the temporal information embedded in the dynamic graphs brings new challenges in analyzing and deploying them.
Calculus of Consent via MARL: Legitimating the Collaborative Governance Supplying Public Goods
Experimental results in an exemplary environment show that our MARL approach is able to demonstrate the effectiveness and necessity of restrictions on individual liberty for collaborative supply of public goods.
Generalized Data Weighting via Class-level Gradient Manipulation
To be specific, GDW unrolls the loss gradient to class-level gradients by the chain rule and reweights the flow of each gradient separately.
Learning Multi-Objective Curricula for Robotic Policy Learning
Various automatic curriculum learning (ACL) methods have been proposed to improve the sample efficiency and final performance of deep reinforcement learning (DRL).
Multi-batch Reinforcement Learning via Sample Transfer and Imitation Learning
Unfortunately, most online reinforcement learning algorithms require a large number of interactions with the environment to learn a reliable control policy.
MOBA: Multi-teacher Model Based Reinforcement Learning
Results show that, compared with SOTA model-free methods, our method can improve the data efficiency and system performance by up to 75% and 10%, respectively.
CE-Dedup: Cost-Effective Convolutional Neural Nets Training based on Image Deduplication
To this end, this paper proposes a framework to assess the impact of the near-duplicate images on CNN training performance, called CE-Dedup.
Memorize, Factorize, or be Naïve: Learning Optimal Feature Interaction Methods for CTR Prediction
As feature interactions bring in non-linearity, they are widely adopted to improve the performance of CTR prediction models.
Ranked #1 on
Click-Through Rate Prediction
on Avazu
Pruning Ternary Quantization
To simultaneously optimize bit-width, model size, and accuracy, we propose pruning ternary quantization (PTQ): a simple, effective, symmetric ternary quantization method.
A Graph Data Augmentation Strategy with Entropy Preservation
Considering the preservation of graph entropy, we propose an effective strategy to generate randomly perturbed training data but maintain both graph topology and graph entropy.
Multi-FR: A Multi-objective Optimization Framework for Multi-stakeholder Fairness-aware Recommendation
To address these limitations, we propose a multi-objective optimization framework for fairness-aware recommendation, Multi-FR, that adaptively balances accuracy and fairness for various stakeholders with Pareto optimality guarantee.
Graph Classification Based on Skeleton and Component Features
Most existing popular methods for learning graph embedding only consider fixed-order global structural features and lack structures hierarchical representation.
Variational Nested Dropout
Nested dropout is a variant of dropout operation that is able to order network parameters or features based on the pre-defined importance during training.
Probabilistic Metric Learning with Adaptive Margin for Top-K Recommendation
Personalized recommender systems are playing an increasingly important role as more content and services become available and users struggle to identify what might interest them.
Knowledge-Enhanced Top-K Recommendation in Poincaré Ball
To effectively make use of the knowledge graph, we propose a recommendation model in the hyperbolic space, which facilitates the learning of the hierarchical structure of knowledge graphs.
Reinforced Epidemic Control: Saving Both Lives and Economy
Saving lives or economy is a dilemma for epidemic control in most cities while smart-tracing technology raises people's privacy concerns.
Representation Learning of Graphs Using Graph Convolutional Multilayer Networks Based on Motifs
The graph structure is a commonly used data storage mode, and it turns out that the low-dimensional embedded representation of nodes in the graph is extremely useful in various typical tasks, such as node classification, link prediction , etc.
Feature Statistics Guided Efficient Filter Pruning
Building compact convolutional neural networks (CNNs) with reliable performance is a critical but challenging task, especially when deploying them in real-world applications.
Out-of-Distribution Detection for Skin Lesion Images with Deep Isolation Forest
In this paper, we study the problem of out-of-distribution detection in skin disease images.
Memory Augmented Graph Neural Networks for Sequential Recommendation
In addition to the modeling of user interests, we employ a bilinear function to capture the co-occurrence patterns of related items.
Connecting First and Second Order Recurrent Networks with Deterministic Finite Automata
We propose an approach that connects recurrent networks with different orders of hidden interaction with regular grammars of different levels of complexity.
Shapley Homology: Topological Analysis of Sample Influence for Neural Networks
This has motivated different research areas such as data poisoning, model improvement, and explanation of machine learning models.
Boosting Image Recognition with Non-differentiable Constraints
In this paper, we study the problem of image recognition with non-differentiable constraints.
Hierarchical Gating Networks for Sequential Recommendation
However, with the tremendous increase of users and items, sequential recommender systems still face several challenging problems: (1) the hardness of modeling the long-term user interests from sparse implicit feedback; (2) the difficulty of capturing the short-term user interests given several items the user just accessed.
Ranked #1 on
Recommendation Systems
on Amazon-CDs
(Recall@10 metric)
Gated Attentive-Autoencoder for Content-Aware Recommendation
In particular, a word-level and a neighbor-level attention module are integrated with the autoencoder.
Verification of Recurrent Neural Networks Through Rule Extraction
The verification problem for neural networks is verifying whether a neural network will suffer from adversarial samples, or approximating the maximal allowed scale of adversarial perturbation that can be endured.
Point-of-Interest Recommendation: Exploiting Self-Attentive Autoencoders with Neighbor-Aware Influence
To incorporate the geographical context information, we propose a neighbor-aware decoder to make users' reachability higher on the similar and nearby neighbors of checked-in POIs, which is achieved by the inner product of POI embeddings together with the radial basis function (RBF) kernel.
A Comparative Study of Rule Extraction for Recurrent Neural Networks
Then we empirically evaluate different recurrent networks for their performance of DFA extraction on all Tomita grammars.
An Empirical Evaluation of Rule Extraction from Recurrent Neural Networks
Rule extraction from black-box models is critical in domains that require model validation before implementation, as can be the case in credit scoring and medical diagnosis.
Learning Adversary-Resistant Deep Neural Networks
Despite the superior performance of DNNs in these applications, it has been recently shown that these models are susceptible to a particular type of attack that exploits a fundamental flaw in their design.
Using Non-invertible Data Transformations to Build Adversarial-Robust Neural Networks
Deep neural networks have proven to be quite effective in a wide variety of machine learning tasks, ranging from improved speech recognition systems to advancing the development of autonomous vehicles.
Adversary Resistant Deep Neural Networks with an Application to Malware Detection
However, after a thorough analysis of the fundamental flaw in DNNs, we discover that the effectiveness of current defenses is limited and, more importantly, cannot provide theoretical guarantees as to their robustness against adversarial sampled-based attacks.
