arXiv subjects

Haipeng Chen

Publications and source records attributed to Haipeng Chen.

47 records · Page 3Linked to original sources

arXiv2021

M2P2: Multimodal Persuasion Prediction using Adaptive Fusion

Identifying persuasive speakers in an adversarial environment is a critical task. In a national election, politicians would like to have persuasive speakers campaign on their behalf. When a company faces adverse publicity, they would like to engage persuasive advocates for their position in the presence of adversaries who are critical of them. Debates represent a common platform for these forms of adversarial persuasion. This paper solves two problems: the Debate Outcome Prediction (DOP) problem predicts who wins a debate while the Intensity of Persuasion Prediction (IPP) problem predicts the change in the number of votes before and after a speaker speaks. Though DOP has been previously studied, we are the first to study IPP. Past studies on DOP fail to leverage two important aspects of multimodal data: 1) multiple modalities are often semantically aligned, and 2) different modalities may provide diverse information for prediction. Our M2P2 (Multimodal Persuasion Prediction) framework is the first to use multimodal (acoustic, visual, language) data to solve the IPP problem. To leverage the alignment of different modalities while maintaining the diversity of the cues they provide, M2P2 devises a novel adaptive fusion learning framework which fuses embeddings obtained from two modules -- an alignment module that extracts shared information between modalities and a heterogeneity module that learns the weights of different modalities with guidance from three separately trained unimodal reference models. We test M2P2 on the popular IQ2US dataset designed for DOP. We also introduce a new dataset called QPS (from Qipashuo, a popular Chinese debate TV show ) for IPP. M2P2 significantly outperforms 4 recent baselines on both datasets.

cs.CV↗

arXiv2021

Dimensions of the popcorn graph

The 'popcorn function' isThe `popcorn function' is a well-known and important example in real analysis with many interesting features. We prove that the box dimension of the graph of the popcorn function is 4/3, as well as computing the Assouad dimension and Assouad spectrum. The main ingredients include Duffin-Schaeffer type estimates from Diophantine approximation and the Chung-Erdős inequality from probability theory.

math.MG↗

arXiv2021

Robust Reinforcement Learning Under Minimax Regret for Green Security

Green security domains feature defenders who plan patrols in the face of uncertainty about the adversarial behavior of poachers, illegal loggers, and illegal fishers. Importantly, the deterrence effect of patrols on adversaries' future behavior makes patrol planning a sequential decision-making problem. Therefore, we focus on robust sequential patrol planning for green security following the minimax regret criterion, which has not been considered in the literature. We formulate the problem as a game between the defender and nature who controls the parameter values of the adversarial behavior and design an algorithm MIRROR to find a robust policy. MIRROR uses two reinforcement learning-based oracles and solves a restricted game considering limited defender strategies and parameter values. We evaluate MIRROR on real-world poaching data.

cs.LG↗

arXiv2021

Contingency-Aware Influence Maximization: A Reinforcement Learning Approach

The influence maximization (IM) problem aims at finding a subset of seed nodes in a social network that maximize the spread of influence. In this study, we focus on a sub-class of IM problems, where whether the nodes are willing to be the seeds when being invited is uncertain, called contingency-aware IM. Such contingency aware IM is critical for applications for non-profit organizations in low resource communities (e.g., spreading awareness of disease prevention). Despite the initial success, a major practical obstacle in promoting the solutions to more communities is the tremendous runtime of the greedy algorithms and the lack of high performance computing (HPC) for the non-profits in the field -- whenever there is a new social network, the non-profits usually do not have the HPCs to recalculate the solutions. Motivated by this and inspired by the line of works that use reinforcement learning (RL) to address combinatorial optimization on graphs, we formalize the problem as a Markov Decision Process (MDP), and use RL to learn an IM policy over historically seen networks, and generalize to unseen networks with negligible runtime at test phase. To fully exploit the properties of our targeted problem, we propose two technical innovations that improve the existing methods, including state-abstraction and theoretically grounded reward shaping. Empirical results show that our method achieves influence as high as the state-of-the-art methods for contingency-aware IM, while having negligible runtime at test phase.

cs.SI↗

arXiv2021

On Hölder maps and prime gaps

Let $p_n$ denote the $n$th prime, and consider the function $1/n \mapsto 1/p_n$ which maps the reciprocals of the positive integers bijectively to the reciprocals of the primes. We show that Hölder continuity of this function is equivalent to a parameterised family of Cramér type estimates on the gaps between successive primes. Here the parameterisation comes from the Hölder exponent. In particular, we show that Cramér's conjecture is equivalent to the map $1/n \mapsto 1/p_n$ being Lipschitz. On the other hand, we show that the inverse map $1/p_n \mapsto 1/n$ is Hölder of all orders but not Lipshitz and this is independent of Cramér's conjecture.

math.NT↗

arXiv2021

Active Screening for Recurrent Diseases: A Reinforcement Learning Approach

Active screening is a common approach in controlling the spread of recurring infectious diseases such as tuberculosis and influenza. In this approach, health workers periodically select a subset of population for screening. However, given the limited number of health workers, only a small subset of the population can be visited in any given time period. Given the recurrent nature of the disease and rapid spreading, the goal is to minimize the number of infections over a long time horizon. Active screening can be formalized as a sequential combinatorial optimization over the network of people and their connections. The main computational challenges in this formalization arise from i) the combinatorial nature of the problem, ii) the need of sequential planning and iii) the uncertainties in the infectiousness states of the population. Previous works on active screening fail to scale to large time horizon while fully considering the future effect of current interventions. In this paper, we propose a novel reinforcement learning (RL) approach based on Deep Q-Networks (DQN), with several innovative adaptations that are designed to address the above challenges. First, we use graph convolutional networks (GCNs) to represent the Q-function that exploit the node correlations of the underlying contact network. Second, to avoid solving a combinatorial optimization problem in each time period, we decompose the node set selection as a sub-sequence of decisions, and further design a two-level RL framework that solves the problem in a hierarchical way. Finally, to speed-up the slow convergence of RL which arises from reward sparseness, we incorporate ideas from curriculum learning into our hierarchical RL approach. We evaluate our RL algorithm on several real-world networks.

cs.LG↗

arXiv2021

EvaLDA: Efficient Evasion Attacks Towards Latent Dirichlet Allocation

As one of the most powerful topic models, Latent Dirichlet Allocation (LDA) has been used in a vast range of tasks, including document understanding, information retrieval and peer-reviewer assignment. Despite its tremendous popularity, the security of LDA has rarely been studied. This poses severe risks to security-critical tasks such as sentiment analysis and peer-reviewer assignment that are based on LDA. In this paper, we are interested in knowing whether LDA models are vulnerable to adversarial perturbations of benign document examples during inference time. We formalize the evasion attack to LDA models as an optimization problem and prove it to be NP-hard. We then propose a novel and efficient algorithm, EvaLDA to solve it. We show the effectiveness of EvaLDA via extensive empirical evaluations. For instance, in the NIPS dataset, EvaLDA can averagely promote the rank of a target topic from 10 to around 7 by only replacing 1% of the words with similar words in a victim document. Our work provides significant insights into the power and limitations of evasion attacks to LDA models.

cs.LG↗

arXiv2021

Aggregated Multi-GANs for Controlled 3D Human Motion Prediction

Human motion prediction from historical pose sequence is at the core of many applications in machine intelligence. However, in current state-of-the-art methods, the predicted future motion is confined within the same activity. One can neither generate predictions that differ from the current activity, nor manipulate the body parts to explore various future possibilities. Undoubtedly, this greatly limits the usefulness and applicability of motion prediction. In this paper, we propose a generalization of the human motion prediction task in which control parameters can be readily incorporated to adjust the forecasted motion. Our method is compelling in that it enables manipulable motion prediction across activity types and allows customization of the human movement in a variety of fine-grained ways. To this aim, a simple yet effective composite GAN structure, consisting of local GANs for different body parts and aggregated via a global GAN is presented. The local GANs game in lower dimensions, while the global GAN adjusts in high dimensional space to avoid mode collapse. Extensive experiments show that our method outperforms state-of-the-art. The codes are available at https://github.com/herolvkd/AM-GAN.

cs.CV↗

arXiv2020

Learning Behaviors with Uncertain Human Feedback

Human feedback is widely used to train agents in many domains. However, previous works rarely consider the uncertainty when humans provide feedback, especially in cases that the optimal actions are not obvious to the trainers. For example, the reward of a sub-optimal action can be stochastic and sometimes exceeds that of the optimal action, which is common in games or real-world. Trainers are likely to provide positive feedback to sub-optimal actions, negative feedback to the optimal actions and even do not provide feedback in some confusing situations. Existing works, which utilize the Expectation Maximization (EM) algorithm and treat the feedback model as hidden parameters, do not consider uncertainties in the learning environment and human feedback. To address this challenge, we introduce a novel feedback model that considers the uncertainty of human feedback. However, this incurs intractable calculus in the EM algorithm. To this end, we propose a novel approximate EM algorithm, in which we approximate the expectation step with the Gradient Descent method. Experimental results in both synthetic scenarios and two real-world scenarios with human participants demonstrate the superior performance of our proposed approach.

cs.AI↗

arXiv2020

Lower Assouad type dimensions of uniformly perfect sets in doubling metric spaces

In this paper, we are concerned with the relationship among the lower Assouad type dimensions. For uniformly perfect sets in doubling metric spaces, we obtain a variational result between two different but closely related lower Assouad spectra. As an application, we show that the limit of the lower Assouad spectrum as $θ$ tends to 1 equals to the quasi-lower Assouad dimension, which provides an equivalent definition to the latter. On the other hand, although the limit of the lower Assouad spectrum as $θ$ tends to 0 exists, there exist uniformly perfect sets such that this limit is not equal to the lower box-counting dimension. Moreover, by the example of Cantor cut-out sets, we show that the new definition of quasi lower Assouad dimension is more accessible, and indicate that the lower Assouad dimension could be strictly smaller than the lower spectra and the quasi lower Assouad dimension.

math.CA↗

arXiv2018

A time-efficient frame size adjustment based approach for RFID anti-collision

Fast and efficient identify a large number of RFID tags in the region of interest is a critical issue in various RFID applications. In this paper, a novel sub-frame-based algorithm with a time-efficient frame size adjustment strategy to reduce the time complexity for EPCglobal C1 Gen2 UHF RFID standard is proposed. By observing the slot statistics in a sub-frame, the tag quantity is estimated by the reader, which afterwards efficiently calculates an optimal frame size to fit the unread tags. Only when the expected time efficiency in the oncoming frame is higher than that in the previous frame, the reader starts the new identification round with the updated frame. Moreover, the estimation of the proposed algorithm is implemented by the look-up tables, which allows dramatically reduction in the computational complexity. Simulation results show noticeable throughput, time efficiency, and identification speed improvements of the proposed solution over the existing approaches.

cs.NI↗