Computing Research Repository

Waudby-Smith, Ian; Wu, Lili; Ramdas, Aaditya; Karampatziakis, Nikos; Mineiro, Paul

doi: 10.48550/arxiv.2210.10768pmid: N/A

Abstract:Contextual bandit algorithms are ubiquitous tools for active sequential experimentation in healthcare and the tech industry. They involve online learning algorithms that adaptively learn policies over time to map observed contexts $X_t$ to actions $A_t$ in an attempt to maximize stochastic rewards $R_t$. This adaptivity raises interesting but hard statistical inference questions, especially counterfactual ones: for example, it is often of interest to estimate the properties of a hypothetical policy that is different from the logging policy that was used to collect the data -- a problem known as ``off-policy evaluation'' (OPE). Using modern martingale techniques, we present a comprehensive framework for OPE inference that relax unnecessary conditions made in some past works, significantly improving on them both theoretically and empirically. Importantly, our methods can be employed while the original experiment is still running (that is, not necessarily post-hoc), when the logging policy may be itself changing (due to learning), and even if the context distributions are a highly dependent time-series (such as if they are drifting over time). More concretely, we derive confidence sequences for various functionals of interest in OPE. These include doubly robust ones for time-varying off-policy mean reward values, but also confidence bands for the entire cumulative distribution function of the off-policy reward distribution. All of our methods (a) are valid at arbitrary stopping times (b) only make nonparametric assumptions, (c) do not require importance weights to be uniformly bounded and if they are, we do not need to know these bounds, and (d) adapt to the empirical variance of our estimators. In summary, our methods enable anytime-valid off-policy inference using adaptively collected contextual bandit data.

Wei, Jianxin; Bao, Ergute; Xiao, Xiaokui; Yang, Yin

doi: 10.1145/3548606.3560562pmid: N/A

Abstract:Nowadays, differential privacy (DP) has become a well-accepted standard for privacy protection, and deep neural networks (DNN) have been immensely successful in machine learning. The combination of these two techniques, i.e., deep learning with differential privacy, promises the privacy-preserving release of high-utility models trained with sensitive data such as medical records. A classic mechanism for this purpose is DP-SGD, which is a differentially private version of the stochastic gradient descent (SGD) optimizer commonly used for DNN training. Subsequent approaches have improved various aspects of the model training process, including noise decay schedule, model architecture, feature engineering, and hyperparameter tuning. However, the core mechanism for enforcing DP in the SGD optimizer remains unchanged ever since the original DP-SGD algorithm, which has increasingly become a fundamental barrier limiting the performance of DP-compliant machine learning solutions. Motivated by this, we propose DPIS, a novel mechanism for differentially private SGD training that can be used as a drop-in replacement of the core optimizer of DP-SGD, with consistent and significant accuracy gains over the latter. The main idea is to employ importance sampling (IS) in each SGD iteration for mini-batch selection, which reduces both sampling variance and the amount of random noise injected to the gradients that is required to satisfy DP. Integrating IS into the complex mathematical machinery of DP-SGD is highly non-trivial. DPIS addresses the challenge through novel mechanism designs, fine-grained privacy analysis, efficiency enhancements, and an adaptive gradient clipping optimization. Extensive experiments on four benchmark datasets, namely MNIST, FMNIST, CIFAR-10 and IMDb, demonstrate the superior effectiveness of DPIS over existing solutions for deep learning with differential privacy.

Shang, Hongbing; Yang, Qixiu; Sun, Chuang; Chen, Xuefeng; Yan, Ruqiang

doi: 10.1016/j.jmsy.2024.08.009pmid: N/A

Abstract:Aero-engine is the core component of aircraft and other spacecraft. The high-speed rotating blades provide power by sucking in air and fully combusting, and various defects will inevitably occur, threatening the operation safety of aero-engine. Therefore, regular inspections are essential for such a complex system. However, existing traditional technology which is borescope inspection is labor-intensive, time-consuming, and experience-dependent. To endow this technology with intelligence, a novel superpixel perception graph neural network (SPGNN) is proposed by utilizing a multi-stage graph convolutional network (MSGCN) for feature extraction and superpixel perception region proposal network (SPRPN) for region proposal. First, to capture complex and irregular textures, the images are transformed into a series of patches, to obtain their graph representations. Then, MSGCN composed of several GCN blocks extracts graph structure features and performs graph information processing at graph level. Last but not least, the SPRPN is proposed to generate perceptual bounding boxes by fusing graph representation features and superpixel perception features. Therefore, the proposed SPGNN always implements feature extraction and information transmission at the graph level in the whole SPGNN pipeline, to alleviate the reduction of receptive field and information loss. To verify the effectiveness of SPGNN, we construct a simulated blade dataset with 3000 images. A public aluminum dataset is also used to validate the performances of different methods. The experimental results demonstrate that the proposed SPGNN has superior performance compared with the state-of-the-art methods.

Gheorghiu, Alexander V.; Pym, David J.

doi: 10.48550/arxiv.2210.05344pmid: N/A

Abstract:Proof-theoretic semantics (P-tS) is the approach to meaning in logic based on 'proof' (as opposed to 'truth'). There are two major approaches to P-tS: proof-theoretic validity (P-tV) and base-extension semantics (B-eS). The former is a semantics of arguments, and the latter is a semantics of logical constants. This paper demonstrates that the B-eS for intuitionistic propositional logic (IPL) encapsulates the declarative content of a version of P-tV based on the elimination rules. This explicates how the B-eS for IPL works, and shows the completeness of this version of P-tV.

Maarouf, Abdurahman; Pröllochs, Nicolas; Feuerriegel, Stefan

doi: 10.1145/3641025pmid: N/A

Abstract:Online hate speech is responsible for violent attacks such as, e.g., the Pittsburgh synagogue shooting in 2018, thereby posing a significant threat to vulnerable groups and society in general. However, little is known about what makes hate speech on social media go viral. In this paper, we collect N = 25,219 cascades with 65,946 retweets from X (formerly known as Twitter) and classify them as hateful vs. normal. Using a generalized linear regression, we then estimate differences in the spread of hateful vs. normal content based on author and content variables. We thereby identify important determinants that explain differences in the spreading of hateful vs. normal content. For example, hateful content authored by verified users is disproportionally more likely to go viral than hateful content from non-verified ones: hateful content from a verified user (as opposed to normal content) has a 3.5 times larger cascade size, a 3.2 times longer cascade lifetime, and a 1.2 times larger structural virality. Altogether, we offer novel insights into the virality of hate speech on social media.

Muttakin, Md Nurul; Hossain, Md Iqbal; Rahman, Md Saidur

doi: 10.48550/arxiv.2210.11174pmid: N/A

Abstract:Overlapping community detection is a key problem in graph mining. Some research has considered applying graph convolutional networks (GCN) to tackle the problem. However, it is still challenging to incorporate deep graph convolutional networks in the case of general irregular graphs. In this study, we design a deep dynamic residual graph convolutional network (DynaResGCN) based on our novel dynamic dilated aggregation mechanisms and a unified end-to-end encoder-decoder-based framework to detect overlapping communities in networks. The deep DynaResGCN model is used as the encoder, whereas we incorporate the Bernoulli-Poisson (BP) model as the decoder. Consequently, we apply our overlapping community detection framework in a research topics dataset without having ground truth, a set of networks from Facebook having a reliable (hand-labeled) ground truth, and in a set of very large co-authorship networks having empirical (not hand-labeled) ground truth. Our experimentation on these datasets shows significantly superior performance over many state-of-the-art methods for the detection of overlapping communities in networks.

Guo, He

doi: 10.1002/jgt.23183pmid: N/A

Abstract:A generalization of the famous Caccetta--Häggkvist conjecture, suggested by Aharoni [Rainbow triangles and the Caccetta-Häggkvist conjecture, J. Graph Theory (2019)], is that any family $\mathcal{F}=(F_1, \ldots,F_n)$ of sets of edges in $K_n$, each of size $k$, has a rainbow cycle of length at most $\lceil \frac{n}{k}\rceil$. In [Rainbow cycles for families of matchings, Israel J. Math. (2023)] and [Non-uniform degrees and rainbow versions of the Caccetta-Häggkvist conjecture, SIAM J. Discrete Math. (2023)] it was shown that asymptotically this can be improved to $O(\log n)$ if all sets are matchings of size 2, or all are triangles. We show that the same is true in the mixed case, i.e., if each $F_i$ is either a matching of size 2 or a triangle. We also study the case that each $F_i$ is a matching of size 2 or a single edge, or each $F_i$ is a triangle or a single edge, and in each of these cases we determine the threshold proportion between the types, beyond which the rainbow girth goes from linear to logarithmic.

Bhutani, Nancy; Pachal, Soumen; Achar, Avinash

doi: 10.48550/arxiv.2210.01655pmid: N/A

Abstract:Arrival/Travel times for public transit exhibit variability on account of factors like seasonality, dwell times at bus stops, traffic signals, travel demand fluctuation etc. The developing world in particular is plagued by additional factors like lack of lane discipline, excess vehicles, diverse modes of transport and so on. This renders the bus arrival time prediction (BATP) to be a challenging problem especially in the developing world. A novel data-driven model based on recurrent neural networks (RNNs) is proposed for BATP (in real-time) in the current work. The model intelligently incorporates both spatial and temporal correlations in a unique (non-linear) fashion distinct from existing approaches. In particular, we propose a Gated Recurrent Unit (GRU) based Encoder-Decoder(ED) OR Seq2Seq RNN model (originally introduced for language translation) for BATP. The geometry of the dynamic real time BATP problem enables a nice fit with the Encoder-Decoder based RNN structure. We feed relevant additional synchronized inputs (from previous trips) at each step of the decoder (a feature classically unexplored in machine translation applications). Further motivated from accurately modelling congestion influences on travel time prediction, we additionally propose to use a bidirectional layer at the decoder (something unexplored in other time-series based ED application contexts). The effectiveness of the proposed algorithms is demonstrated on real field data collected from challenging traffic conditions. Our experiments indicate that the proposed method outperforms diverse existing state-of-art data-driven approaches proposed for the same problem.

Paltenghi, Matteo; Pandita, Rahul; Henley, Austin Z.; Ziegler, Albert

doi: 10.48550/arxiv.2210.05506pmid: N/A

Abstract:Recent neural models of code, such as OpenAI Codex and AlphaCode, have demonstrated remarkable proficiency at code generation due to the underlying attention mechanism. However, it often remains unclear how the models actually process code, and to what extent their reasoning and the way their attention mechanism scans the code matches the patterns of developers. A poor understanding of the model reasoning process limits the way in which current neural models are leveraged today, so far mostly for their raw prediction. To fill this gap, this work studies how the processed attention signal of three open large language models - CodeGen, InCoder and GPT-J - agrees with how developers look at and explore code when each answers the same sensemaking questions about code. Furthermore, we contribute an open-source eye-tracking dataset comprising 92 manually-labeled sessions from 25 developers engaged in sensemaking tasks. We empirically evaluate five heuristics that do not use the attention and ten attention-based post-processing approaches of the attention signal of CodeGen against our ground truth of developers exploring code, including the novel concept of follow-up attention which exhibits the highest agreement between model and human attention. Our follow-up attention method can predict the next line a developer will look at with 47% accuracy. This outperforms the baseline prediction accuracy of 42.3%, which uses the session history of other developers to recommend the next line. These results demonstrate the potential of leveraging the attention signal of pre-trained models for effective code exploration.

Ma, Lin; Chen, Longrui; Zhang, Yan; Chu, Mengdi; Jiang, Wenjie; Shen, Jiahao; Li, Chuxuan; Shi, Yifeng; Luo, Nairui; Yuan, Jirui; Zhou, Guyue; Gong, Jiangtao

doi: 10.48550/arxiv.2210.08731pmid: N/A

Abstract:Pedestrians' safety is a crucial factor in assessing autonomous driving scenarios. However, pedestrian safety evaluation is rarely considered by existing autonomous driving simulation platforms. This paper proposes a pedestrian safety evaluation method for autonomous driving, in which not only the collision events but also the conflict events together with the characteristics of pedestrians are fully considered. Moreover, to apply the pedestrian safety evaluation system, we construct a high-fidelity simulation framework embedded with pedestrian safety-critical characteristics. We demonstrate our simulation framework and pedestrian safety evaluation with a comparative experiment with two kinds of autonomous driving perception algorithms -- single-vehicle perception and vehicle-to-infrastructure (V2I) cooperative perception. The results show that our framework can evaluate different autonomous driving algorithms with detailed and quantitative pedestrian safety indexes. To this end, the proposed simulation method and framework can be used to access different autonomous driving algorithms and evaluate pedestrians' safety performance in future autonomous driving simulations, which can inspire more pedestrian-friendly autonomous driving algorithms.