Session

Applications 2

Moderator: Qibin Zhao



Abstract:

Chat is not available.

Wed 21 July 19:00 - 19:20 PDT

(Oral)
RNN with Particle Flow for Probabilistic Spatio-temporal Forecasting

Soumyasundar Pal · Liheng Ma · Yingxue Zhang · Mark Coates

Spatio-temporal forecasting has numerous applications in analyzing wireless, traffic, and financial networks. Many classical statistical models often fall short in handling the complexity and high non-linearity present in time-series data. Recent advances in deep learning allow for better modelling of spatial and temporal dependencies. While most of these models focus on obtaining accurate point forecasts, they do not characterize the prediction uncertainty. In this work, we consider the time-series data as a random realization from a nonlinear state-space model and target Bayesian inference of the hidden states for probabilistic forecasting. We use particle flow as the tool for approximating the posterior distribution of the states, as it is shown to be highly effective in complex, high-dimensional settings. Thorough experimentation on several real world time-series datasets demonstrates that our approach provides better characterization of uncertainty while maintaining comparable accuracy to the state-of-the-art point forecasting methods.

[ Paper PDF ] [ ]
Wed 21 July 19:20 - 19:25 PDT

(Spotlight)
A Differentiable Point Process with Its Application to Spiking Neural Networks

Hiroshi Kajino

This paper is concerned about a learning algorithm for a probabilistic model of spiking neural networks (SNNs). Jimenez Rezende & Gerstner (2014) proposed a stochastic variational inference algorithm to train SNNs with hidden neurons. The algorithm updates the variational distribution using the score function gradient estimator, whose high variance often impedes the whole learning algorithm. This paper presents an alternative gradient estimator for SNNs based on the path-wise gradient estimator. The main technical difficulty is a lack of a general method to differentiate a realization of an arbitrary point process, which is necessary to derive the path-wise gradient estimator. We develop a differentiable point process, which is the technical highlight of this paper, and apply it to derive the path-wise gradient estimator for SNNs. We investigate the effectiveness of our gradient estimator through numerical simulation.

[ Paper PDF ] [ ]
Wed 21 July 19:25 - 19:30 PDT

(Spotlight)
Diffusion Source Identification on Networks with Statistical Confidence

Quinlan Dawkins · Tianxi Li · Haifeng Xu

Diffusion source identification on networks is a problem of fundamental importance in a broad class of applications, including controlling the spreading of rumors on social media, identifying a computer virus over cyber networks, or identifying the disease center during epidemiology. Though this problem has received significant recent attention, most known approaches are well-studied in only very restrictive settings and lack theoretical guarantees for more realistic networks. We introduce a statistical framework for the study of this problem and develop a confidence set inference approach inspired by hypothesis testing. Our method efficiently produces a small subset of nodes, which provably covers the source node with any pre-specified confidence level without restrictive assumptions on network structures. To our knowledge, this is the first diffusion source identification method with a practically useful theoretical guarantee on general networks. We demonstrate our approach via extensive synthetic experiments on well-known random network models, a large data set of real-world networks as well as a mobility network between cities concerning the COVID-19 spreading in January 2020.

[ Paper PDF ] [ ]
Wed 21 July 19:30 - 19:35 PDT

(Spotlight)
Quantifying Ignorance in Individual-Level Causal-Effect Estimates under Hidden Confounding

Andrew Jesson · Sören Mindermann · Yarin Gal · Uri Shalit

We study the problem of learning conditional average treatment effects (CATE) from high-dimensional, observational data with unobserved confounders. Unobserved confounders introduce ignorance---a level of unidentifiability---about an individual's response to treatment by inducing bias in CATE estimates. We present a new parametric interval estimator suited for high-dimensional data, that estimates a range of possible CATE values when given a predefined bound on the level of hidden confounding. Further, previous interval estimators do not account for ignorance about the CATE associated with samples that may be underrepresented in the original study, or samples that violate the overlap assumption. Our interval estimator also incorporates model uncertainty so that practitioners can be made aware of such out-of-distribution data. We prove that our estimator converges to tight bounds on CATE when there may be unobserved confounding and assess it using semi-synthetic, high-dimensional datasets.

[ Paper PDF ] [ ]
Wed 21 July 19:35 - 19:40 PDT

(Spotlight)
Making Paper Reviewing Robust to Bid Manipulation Attacks

Ruihan Wu · Chuan Guo · Felix Wu · Rahul Kidambi · Laurens van der Maaten · Kilian Weinberger

Most computer science conferences rely on paper bidding to assign reviewers to papers. Although paper bidding enables high-quality assignments in days of unprecedented submission numbers, it also opens the door for dishonest reviewers to adversarially influence paper reviewing assignments. Anecdotal evidence suggests that some reviewers bid on papers by "friends" or colluding authors, even though these papers are outside their area of expertise, and recommend them for acceptance without considering the merit of the work. In this paper, we study the efficacy of such bid manipulation attacks and find that, indeed, they can jeopardize the integrity of the review process. We develop a novel approach for paper bidding and assignment that is much more robust against such attacks. We show empirically that our approach provides robustness even when dishonest reviewers collude, have full knowledge of the assignment system's internal workings, and have access to the system's inputs. In addition to being more robust, the quality of our paper review assignments is comparable to that of current, non-robust assignment approaches.

[ Paper PDF ] [ ]
Wed 21 July 19:40 - 19:45 PDT

(Spotlight)
Model Distillation for Revenue Optimization: Interpretable Personalized Pricing

Max Biggs · Wei Sun · Markus Ettl

Data-driven pricing strategies are becoming increasingly common, where customers are offered a personalized price based on features that are predictive of their valuation of a product. It is desirable for this pricing policy to be simple and interpretable, so it can be verified, checked for fairness, and easily implemented. However, efforts to incorporate machine learning into a pricing framework often lead to complex pricing policies that are not interpretable, resulting in slow adoption in practice. We present a novel, customized, prescriptive tree-based algorithm that distills knowledge from a complex black-box machine learning algorithm, segments customers with similar valuations and prescribes prices in such a way that maximizes revenue while maintaining interpretability. We quantify the regret of a resulting policy and demonstrate its efficacy in applications with both synthetic and real-world datasets.

[ Paper PDF ] [ ]
Wed 21 July 19:45 - 19:50 PDT

(Spotlight)
Learning Generalized Intersection Over Union for Dense Pixelwise Prediction

Jiaqian Yu · Jingtao Xu · Yiwei Chen · Weiming Li · Qiang Wang · ByungIn Yoo · Jae-Joon Han

Intersection over union (IoU) score, also named Jaccard Index, is one of the most fundamental evaluation methods in machine learning. The original IoU computation cannot provide non-zero gradients and thus cannot be directly optimized by nowadays deep learning methods. Several recent works generalized IoU for bounding box regression, but they are not straightforward to adapt for pixelwise prediction. In particular, the original IoU fails to provide effective gradients for the non-overlapping and location-deviation cases, which results in performance plateau. In this paper, we propose PixIoU, a generalized IoU for pixelwise prediction that is sensitive to the distance for non-overlapping cases and the locations in prediction. We provide proofs that PixIoU holds many nice properties as the original IoU. To optimize the PixIoU, we also propose a loss function that is proved to be submodular, hence we can apply the Lov\'asz functions, the efficient surrogates for submodular functions for learning this loss. Experimental results show consistent performance improvements by learning PixIoU over the original IoU for several different pixelwise prediction tasks on Pascal VOC, VOT-2020 and Cityscapes.

[ Paper PDF ] [ ]
Wed 21 July 19:50 - 19:55 PDT

(Q&A)
Q&A

[ ]