skip to main content


Title: Efficient Multiple Objective Optimization for Fair Misinformation Detection
Multiple-objective optimization (MOO) aims to simultaneously optimize multiple conflicting objectives and has found important applications in machine learning, such as simultaneously minimizing classification and fairness losses. At an optimum, further optimizing one objective will necessarily increase at least another objective, and decision-makers need to comprehensively explore multiple optima to pin-point one final solution. We address the efficiency of exploring the Pareto front that contains all optima. First, stochastic multi-gradient descent (SMGD) takes time to converge to the Pareto front with large neural networks and datasets. Instead, we explore the Pareto front as a manifold from a few initial optima, based on a predictor-corrector method. Second, for each exploration step, the predictor iteratively solves a large-scale linear system that scales quadratically in the number of model parameters, and requires one backpropagation to evaluate a second-order Hessian-vector product per iteration of the solver. We propose a Gauss-Newton approximation that scales linearly, and that requires only first-order inner-product per iteration. T hird, we explore different linear system solvers, including the MINRES and conjugate gradient methods for approximately solving the linear systems. The innovations make predictor-corrector efficient for large networks and datasets. Experiments on a fair misinformation detection task show that 1) the predictor-corrector method can find Pareto fronts better than or similar to SMGD with less time, and 2) the proposed first-order method does not harm the quality of the Pareto front identified by the second-order method, while further reducing running time.  more » « less
Award ID(s):
2008155
NSF-PAR ID:
10477854
Author(s) / Creator(s):
; ; ; ;
Publisher / Repository:
IEEE
Date Published:
Journal Name:
2022 IEEE International Conference on Big Data (Big Data)
ISBN:
978-1-6654-8045-1
Page Range / eLocation ID:
16 to 25
Format(s):
Medium: X
Location:
Osaka, Japan
Sponsoring Org:
National Science Foundation
More Like this
  1. Sequences of linear systems arise in the predictor- corrector method when computing the Pareto front for multi- objective optimization. Rather than discarding information gen- erated when solving one system, it may be advantageous to recycle information for subsequent systems. To accomplish this, we seek to reduce the overall cost of computation when solving linear systems using common recycling methods. In this work, we assessed the performance of recycling minimum residual (RMIN- RES) method along with a map between coefficient matrices. For these methods to be fully integrated into the software used in Enouen et al. (2022), there must be working version of each in both Python and PyTorch. Herein, we discuss the challenges we encountered and solutions undertaken (and some ongoing) when computing efficient Python implementations of these recycling strategies. The goal of this project was to implement RMINRES in Python and PyTorch and add it to the established Pareto front code to reduce computational cost. Additionally, we wanted to implement the sparse approximate maps code in Python and PyTorch, so that it can be parallelized in future work. 
    more » « less
  2. We present a policy gradient method for Multi-Objective Reinforcement Learning under unknown, linear preferences. By enforcing Pareto stationarity, a first-order condition for Pareto optimality, we are able to design a simple policy gradient algorithm that approximates the Pareto front and infers the unknown preferences. Our method relies on a projected gradient descent solver that identifies common ascent directions for all objectives. Leveraging the solution of that solver, we introduce Pareto Policy Adaptation (PPA), a loss function that adapts the policy to be optimal with respect to any distribution over preferences. PPA uses implicit differentiation to back-propagate the loss gradient bypassing the operations of the projected gradient descent solver. Our approach is straightforward, easy to implement and can be used with all existing policy gradient and actor-critic methods. We evaluate our method in a series of reinforcement learning tasks 
    more » « less
  3. We present a policy gradient method for Multi-Objective Reinforcement Learning under unknown, linear preferences. By enforcing Pareto stationarity, a first-order condition for Pareto optimality, we are able to design a simple policy gradient al- gorithm that approximates the Pareto front and infers the unknown preferences. Our method relies on a projected gradient descent solver that identifies common ascent directions for all objectives. Leveraging the solution of that solver, we in- troduce Pareto Policy Adaptation (PPA), a loss function that adapts the policy to be optimal with respect to any distribution over preferences. PPA uses implicit differentiation to back-propagate the loss gradient bypassing the operations of the projected gradient descent solver. Our approach is straightforward, easy to imple- ment and can be used with all existing policy gradient and actor-critic methods. We evaluate our method in a series of reinforcement learning tasks. 
    more » « less
  4. Issues of fairness often arise in graphical neural networks used for misinformation detection. However, improving fairness can often come at the cost of reducing accuracy and vice versa. Therefore, we formulate the task of balancing accuracy and fairness as a multi-objective optimization (MOO) problem where we seek to find a set of Pareto optimal solutions. Traditional first-order approaches to solving MOO problems such as multigradient descent can be costly, especially with large neural networks. Instead, we describe a more efficient approach using the predictor-corrector method. Given an initial Pareto optimal point, this approach predicts the direction of a neighboring solution and refines this prediction using a few steps of multigradient descent. We show experimentally that this approach allows for the generation of high-quality Pareto fronts faster than baseline optimization methods. 
    more » « less
  5. Finding diverse and representative Pareto solutions from the Pareto front is a key challenge in multi-objective optimization (MOO). In this work, we propose a novel gradient-based algorithm for profiling Pareto front by using Stein variational gradient descent (SVGD). We also provide a counterpart of our method based on Langevin dynamics. Our methods iteratively update a set of points in a parallel fashion to push them towards the Pareto front using multiple gradient descent, while encouraging the diversity between the particles by using the repulsive force mechanism in SVGD, or diffusion noise in Langevin dynamics. Compared with existing gradient-based methods that require predefined preference functions, our method can work efficiently in high dimensional problems, and can obtain more diverse solutions evenly distributed in the Pareto front. Moreover, our methods are theoretically guaranteed to converge to the Pareto front. We demonstrate the effectiveness of our method, especially the SVGD algorithm, through extensive experiments, showing its superiority over existing gradient-based algorithms. 
    more » « less