Francesco Alesiani
  • Bio
  • Papers
  • News
  • Recent & Upcoming Talks
    • Example Talk
  • Publications
    • ACCELERATING PARTICLE SIMULATIONS USING MACHINE LEARNING AND MOLECULAR DYNAMIC SIMULATIONS
    • Hierarchy-based Clifford Group Equivariant Message Passing Neural Networks
    • Information system for generation of complex molecule by using graph representing molecule
    • Machine learning knowledge management based on lifelong boosting in presence of less data
    • Learning logical rules over graph structured data using message passing
    • Graph Reasoning Networks
    • Higher-Rank Irreducible Cartesian Tensors for Equivariant Message Passing
    • Uncertainty-biased molecular dynamics for learning uniformly accurate interatomic potentials
    • Machine learning for optimized learning of human-understandable logical rules from medical or other data
    • Hyper network machine learning architecture for simulating physical systems
    • Systems and methods for learning human-understandable logical rules from data
    • Method for verifying information
    • LEO Satellite Orbit Prediction with Physics Informed Machine Learning
    • Method and system for scalable multi-task learning with convex clustering
    • Affinity graph extraction and updating systems and methods
    • Partial planar point cloud matching using machine learning with applications in biometric systems
    • Mechanism for reducing information lost in set neural networks
    • Adaptive Message Passing: A General Framework to Mitigate Oversmoothing, Oversquashing, and Underreaching
    • CAPE: channel-attention-based PDE parameter embeddings for SciML
    • Continual Invariant Risk Minimization
    • Continual learning of artificial intelligence systems based on bi-level optimization
    • Continuous-Discrete Message Passing for Graph Logic Reasoning
    • Differentiable MaxSAT Message Passing
    • Gated information bottleneck for generalization in sequential environments
    • Implicit bilevel optimization: Differentiating through bilevel optimization programming
    • Learning neural pde solvers with parameter-guided channel attention
    • Self-tuning Hamiltonian Monte Carlo for accelerated sampling
    • End-to-end channel estimation in communication networks
    • Method and system to differentiate through bilevel optimization problems using machine learning
    • Method for predicting a motion of an object
    • Scalable, accurate and reliable measure of variable dependence and independence, and utilization of the measure to train a neural network
    • BiGrad: Differentiating through bilevel optimization programming
    • Constrained clustering for the capacitated vehicle routing problem (cc-cvrp)
    • Human-centric research for nlp: Towards a definition and guiding questions
    • HyperFNO: Improving the generalization behavior of Fourier Neural Operators
    • Modular-relatedness for continual learning
    • Pdebench: An extensive benchmark for scientific machine learning
    • Principle of relevant information for graph sparsification
    • Principle of Relevant Information for Graph Sparsification (Supp. Material)
    • Method and system for generating robust solutions to optimization problems using machine learning
    • Methods and systems for graph approximation
    • Constrained vehicle routing using clusters
    • Method and system for reliable computation of a program
    • Method for verifying information
    • Bilevel Continual Learning
    • Bilevel Continual Learning
    • Measuring dependence with matrix-based entropy functional
    • Optimization of collection and consolidation operations in cross-border multi-modal distribution networks
    • Reinforcement Learning for Route Optimization with Robustness Guarantees.
    • Towards interpretable multi-task learning using bilevel programming
    • Method for motion planning for autonomous moving objects
    • Learning an interpretable graph structure in multi-task learning
    • Measuring the discrepancy between conditional distributions: Methods, properties and applications
    • Method for robust control of a machine learning system and robust control system
    • System and method for real-time large image homography processing
    • Efficient and scalable multi-task regression on massive number of tasks
    • Robust timetable optimization for bus lines subject to resource and regulatory constraints
    • Method for the continuous processing of two-level data on a system with a plurality of nodes
    • Method and system for providing demand-responsive dispatching of a fleet of transportation vehicles, and a mobility-activity processing module for providing a mobility trace database
    • Method for incident detection in a time-evolving system
    • On learning from inaccurate and incomplete traffic flow data
    • Reinforcement learning-based bus holding for high-frequency services
    • Reliable bus dispatching times by coupling Monte Carlo evaluations with a Genetic Algorithm
    • Locally growing rapid tree (LGRT) motion planning for autonomous driving
    • Remote testimony: How to trust an autonomous vehicle
    • A Scenario-Oriented Approach for Noise Detection on Traffic Flow Data
    • Drift3flow: Freeway-incident prediction using real-time learning
    • D2. 13-Final report eCoMessages
    • 2014 Index IEEE Intelligent Transportation Systems Magazine Vol. 6
    • A probabilistic activity model for predicting the mobility patterns of homogeneous social groups based on social network data
    • Educated rules for the prediction of human mobility patterns based on sparse social media and mobile phone data
    • Opportunistic solution-space reduction techniques for reducing the time complexity of dynamic speed control with microsimulation on motorways
    • Optimization of charging stops for fleet of electric vehicles: A genetic approach
    • Afshin Abdi, Qualcomm Milad Abolpour, University of Oulu Ibrahim Abou-Faycal, American University of Beirut Maria Abu-Sini, Technion
    • D242. 213 (D2. 13) Final report ecoMessages
    • Real-Time Eco-Driving Prototype
    • VTC2013-Spring Technical Programme Committee
    • Cooperative ITS messages for green mobility: an overview from the eCoMove project
    • A Scenario-Oriented approach for Noise detection on Traffic Flow data
    • SubProject No. SP2 SubProject Title Core Technology Integration Workpackage No. WP2. 5 Workpackage Title Integration and Verification Task No. 2.5. 3 Task Title Verification test of
    • Blind receiver for space-time differentially-encoded CDMA systems on multipath fading channels
    • Demonstrator 1 Negotiated Priority at Intersections: The Oslo Case Study
    • Optimal Speed Profile Trajectory Computation for Vehicle Approach at Intersection with Adaptive Traffic Control
    • Regional Scale Real-Time Origin-Destination Matrix Estimation Technique and Deployment Results
    • MAPPING TRAFFIC MANAGEMENT SYSTEMS DATA INTO DETAILED NAVIGATION NETWORKS.
    • CVIS. D. 3.3 Architecture and System Specifications
    • D. FOAM. 3.1 Architecture and System Specifications
    • Satellite-Aided Navigation and Related Applications for Dangerous Transport
    • Differential space-time CDMA with turbo decoding
    • Performance of adaptive modulation techniques in the UMTS system
  • Projects
  • Blog
    • 🎉 Easily create your own simple yet highly customizable blog
    • 🧠 Sharpen your thinking with a second brain
    • 📈 Communicate your results effectively with the best data visualizations
    • 👩🏼‍🏫 Teach academic courses
    • ✅ Manage your projects
  • _Projects
    • Pandas
    • PyTorch
    • scikit-learn
  • Experience
  • Teaching
    • Learn JavaScript
    • Learn Python
  • _Publications
    • An example preprint / working paper
    • An example journal article
    • An example conference paper

Bilevel Continual Learning

Jan 1, 2021·
Francesco Alesiani, Shujian Yu, Wenzhe Yin Ammar Shaker
· 0 min read
Cite
Type
Conference paper
Publication
2021 IEEE International Joint Conference on Neural Networks (IJCNN)
Last updated on Jan 1, 2021
← Method for verifying information Feb 1, 2021
Bilevel Continual Learning Jan 1, 2021 →

© 2024 Francesco Alesiani. This work is licensed under CC BY NC ND 4.0

Published with Hugo Blox Builder — the free, open source website builder that empowers creators.