Publications

Using Graph Algorithms to Pretrain Graph Completion Transformers

Bahare Fatemi

David Vasquez

Christopher Pal

Recent work on Graph Neural Networks has demonstrated that self-supervised pretraining can further enhance performance on downstream graph, … (voir plus)link, and node classification tasks. However, the efficacy of pretraining tasks has not been fully investigated for downstream large knowledge graph completion tasks. Using a contextualized knowledge graph embedding approach, we investigate five different pretraining signals, constructed using several graph algorithms and no external data, as well as their combination. We leverage the versatility of our Transformer-based model to explore graph structure generation pretraining tasks (i.e. path and k-hop neighborhood generation), typically inapplicable to most graph embedding methods. We further propose a new path-finding algorithm guided by information gain and find that it is the best-performing pretraining task across three downstream knowledge graph completion datasets. While using our new path-finding algorithm as a pretraining signal provides 2-3% MRR improvements, we show that pretraining on all signals together gives the best knowledge graph completion results. In a multitask setting that combines all pretraining tasks, our method surpasses the latest and strong performing knowledge graph embedding methods on all metrics for FB15K-237, on MRR and Hit@1 for WN18RRand on MRR and hit@10 for JF17K (a knowledge hypergraph dataset).

2022-10-13

ArXiv (prépublication)

doi.org

arxiv.org

Inductive biases for deep learning of higher-level cognition

Anirudh Goyal

Yoshua Bengio

2022-10-11

Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences (publié)

doi.org

arxiv.org

Lookback for Learning to Branch

Prateek Gupta

Elias B. Khalil

Didier Chételat

Maxime Gasse

Yoshua Bengio

Andrea Lodi

M. Pawan Kumar

The expressive and computationally inexpensive bipartite Graph Neural Networks (GNN) have been shown to be an important component of deep le… (voir plus)arning based Mixed-Integer Linear Program (MILP) solvers. Recent works have demonstrated the effectiveness of such GNNs in replacing the branching (variable selection) heuristic in branch-and-bound (B&B) solvers. These GNNs are trained, offline and on a collection of MILPs, to imitate a very good but computationally expensive branching heuristic, strong branching. Given that B&B results in a tree of sub-MILPs, we ask (a) whether there are strong dependencies exhibited by the target heuristic among the neighboring nodes of the B&B tree, and (b) if so, whether we can incorporate them in our training procedure. Specifically, we find that with the strong branching heuristic, a child node's best choice was often the parent's second-best choice. We call this the "lookback" phenomenon. Surprisingly, the typical branching GNN of Gasse et al. (2019) often misses this simple "answer". To imitate the target behavior more closely by incorporating the lookback phenomenon in GNNs, we propose two methods: (a) target smoothing for the standard cross-entropy loss function, and (b) adding a Parent-as-Target (PAT) Lookback regularizer term. Finally, we propose a model selection framework to incorporate harder-to-formulate objectives such as solving time in the final models. Through extensive experimentation on standard benchmark instances, we show that our proposal results in up to 22% decrease in the size of the B&B tree and up to 15% improvement in the solving times.

2022-10-09

TMLR (accepté)

doi.org

openreview.net

Dissecting adaptive methods in GANs

Samy Jelassi

David Dobre

Arthur Mensch

Yuanzhi Li

Gauthier Gidel

Adaptive methods are a crucial component widely used for training generative adversarial networks (GANs). While there has been some work to … (voir plus)pinpoint the “marginal value of adaptive methods” in standard tasks, it remains unclear why they are still critical for GAN training. In this paper, we formally study how adaptive methods help train GANs; inspired by the grafting method proposed in Agarwal et al. (2020), we separate the magnitude and direction components of the Adam updates, and graft them to the direction and magnitude of SGDA updates respectively. By considering an update rule with the magnitude of the Adam update and the normalized direction of SGD, we empirically show that the adaptive magnitude of Adam is key for GAN training. This motivates us to have a closer look at the class of normalized stochastic gradient descent ascent (nSGDA) methods in the context of GAN training. We propose a synthetic theoretical framework to compare the performance of nSGDA and SGDA for GAN training with neural networks. We prove that in that setting, GANs trained with nSGDA recover all the modes of the true distribution, whereas the same networks trained with SGDA (and any learning rate configuration) suffer from mode collapse. The critical insight in our analysis is that normalizing the gradients forces the discriminator and generator to be updated at the same pace. We also experimentally show that for several datasets, Adam’s performance can be recovered with nSGDA methods.

2022-10-08

ArXiv (prépublication)

doi.org

openreview.net

PipeBERT: High-throughput BERT Inference for ARM Big.LITTLE Multi-core Processors.

Hung-Yang Chang

Seyyed Hasan Mozafari

Cheng Chen

James J. Clark

Brett H. Meyer

Warren J. Gross

2022-10-07

Journal of Signal Processing Systems (publié)

doi.org

Novice Type Error Diagnosis with Natural Language Models

Chuqin Geng

Haolin Ye

Yixuan Li

Tianyu Han

Brigitte Pientka

Xujie Si

Strong static type systems help programmers eliminate many errors without much burden of supplying type annotations. However, this flexibili… (voir plus)ty makes it highly non-trivial to diagnose ill-typed programs, especially for novice programmers. Compared to classic constraint solving and optimization-based approaches, the data-driven approach has shown great promise in identifying the root causes of type errors with higher accuracy. Instead of relying on hand-engineered features, this work explores natural language models for type error localization, which can be trained in an end-to-end fashion without requiring any features. We demonstrate that, for novice type error diagnosis, the language model-based approach significantly outperforms the previous state-of-the-art data-driven approach. Specifically, our model could predict type errors correctly 62% of the time, outperforming the state-of-the-art Nate's data-driven model by 11%, in a more rigorous accuracy metric. Furthermore, we also apply structural probes to explain the performance difference between different language models.

2022-10-06

ArXiv (prépublication)

doi.org

arxiv.org

Towards Safe Mechanical Ventilation Treatment Using Deep Offline Reinforcement Learning

Jacob Shkrob

My Duc Tran

Doina Precup

Sumana Basu

Mechanical ventilation is a key form of life support for patients with pulmonary impairment. Healthcare workers are required to continuously… (voir plus) adjust ventilator settings for each patient, a challenging and time consuming task. Hence, it would be beneficial to develop an automated decision support tool to optimize ventilation treatment. We present DeepVent, a Conservative Q-Learning (CQL) based offline Deep Reinforcement Learning (DRL) agent that learns to predict the optimal ventilator parameters for a patient to promote 90 day survival. We design a clinically relevant intermediate reward that encourages continuous improvement of the patient vitals as well as addresses the challenge of sparse reward in RL. We find that DeepVent recommends ventilation parameters within safe ranges, as outlined in recent clinical trials. The CQL algorithm offers additional safety by mitigating the overestimation of the value estimates of out-of-distribution states/actions. We evaluate our agent using Fitted Q Evaluation (FQE) and demonstrate that it outperforms physicians from the MIMIC-III dataset.

2022-10-04

ArXiv (prépublication)

doi.org

arxiv.org

Functional connectivity subtypes associate robustly with ASD diagnosis

Sebastian G. W. Urchs

Angela Tam

Pierre Orban

Clara A. Moreau

Yassine Benhajali

Hien Duy Nguyen

Alan C. Evans

Lune P Bellec

Our understanding of the changes in functional brain organization in autism is hampered by the extensive heterogeneity that characterizes th… (voir plus)is neurodevelopmental disorder. Data driven clustering offers a straightforward way to decompose autism heterogeneity into subtypes of connectivity and promises an unbiased framework to investigate behavioral symptoms and causative genetic factors. Yet, the robustness and generalizability of functional connectivity subtypes is unknown. Here, we show that a simple hierarchical cluster analysis can robustly relate a given individual and brain network to a connectivity subtype, but that continuous assignments are more robust than discrete ones. We also found that functional connectivity subtypes are moderately associated with the clinical diagnosis of autism, and these associations generalize to independent replication data. We explored systematically 18 different brain networks as we expected them to associate with different behavioral profiles as well as different key regions. Contrary to this prediction, autism functional connectivity subtypes converged on a common topography across different networks, consistent with a compression of the primary gradient of functional brain organization, as previously reported in the literature. Our results support the use of data driven clustering as a reliable data dimensionality reduction technique, where any given dimension only associates moderately with clinical manifestations.

2022-10-03

eLife (publié)

doi.org

Protective effectiveness of prior SARS-CoV-2 infection and hybrid immunity against Omicron infection and severe disease: a systematic review and meta-regression

Niklas Bobrovitz

Harriet Ware

Xiaomeng Ma

Zihan Li

Reza Hosseini

Christian Cao

Anabel Selemon

Mairead Whelan

Zahra Premji

Hanane Issa

Brianna Cheng

L. Abu-Raddad

David L Buckeridge

M. D. Kerkhove

Vanessa Piechotta

Melissa M Higdon

Annelies Wilder-Smith

Isabel Bergeri

Daniel R Feikin

Rahul K. Arora … (voir 2 de plus)

Minal K Patel

Lorenzo Subissi

Background We aimed to systematically review the magnitude and duration of the protective effectiveness of prior infection (PE) and hybrid i… (voir plus)mmunity (HE) against Omicron infection and severe disease. Methods We searched pre-print and peer-reviewed electronic databases for controlled studies from January 1, 2020, to June 1, 2022. Risk of bias (RoB) was assessed using the Risk of Bias In Non-Randomized Studies of Interventions (ROBINS-I)-Tool. We used random-effects meta-regression to estimate the magnitude of protection at 1-month intervals and the average change in protection since the last vaccine dose or infection from 3 months to 6 or 12 months. We compared our estimates of PE and HE to previously published estimates of the magnitude and durability of vaccine effectiveness (VE) against Omicron. Findings Eleven studies of prior infection and 15 studies of hybrid immunity were included. For prior infection, there were 97 estimates (27 at moderate RoB and 70 at serious RoB), with the longest follow up at 15 months. PE against hospitalization or severe disease was 82.5% [71.8-89.7%] at 3 months, and 74.6% [63.1-83.5%] at 12 months. PE against reinfection was 65.2% [52.9-75.9%] at 3 months, and 24.7% [16.4-35.5%] at 12 months. For HE, there were 153 estimates (78 at moderate RoB and 75 at serious RoB), with the longest follow up at 11 months for primary series vaccination and 4 months for first booster vaccination. Against hospitalization or severe disease, HE involving either primary series vaccination or first booster vaccination was consistently >95% for the available follow up. Against reinfection, HE involving primary series vaccination was 69.0% [58.9-77.5%] at 3 months after the most recent infection or vaccination, and 41.8% [31.5-52.8%] at 12 months, while HE involving first booster vaccination was 68.6% [58.8-76.9%] at 3 months, and 46.5% [36.0-57.3%] at 6 months. Against hospitalization or severe disease at 6 months, hybrid immunity with first booster vaccination (effectiveness 95.3% [81.9-98.9%]) or with primary series alone (96.5% [90.2-98.8%]) provided significantly greater protection than prior infection alone (80.1% [70.3-87.2%]), first booster vaccination alone (76.7% [72.5-80.4%]), or primary series alone (64.6% [54.5-73.6%]). Results for protection against reinfection were similar. Interpretation Prior infection and hybrid immunity both provided greater and more sustained protection against Omicron than vaccination alone. All protection estimates waned quickly against infection but remained high for hospitalisation or severe disease. Individuals with hybrid immunity had the highest magnitude and durability of protection against all outcomes, reinforcing the global imperative for vaccination.

2022-10-03

medRxiv (prépublication)

doi.org

Revisiting the Impact of Anti-patterns on Fault-Proneness: A Differentiated Replication

Aurel Ikama

Vincent Du

Philippe Belias

Biruk Asmare Muse

Foutse Khomh

Mohammad Hamdaqa

Anti-patterns manifesting on software code through code smells have been investigated in terms of their prevalence, detection, refactoring, … (voir plus)and impact on software quality attributes. In particular, leveraging heuristics to identify fault-fixing commits, Khomh et al. have found that anti-patterns and code smells have an impact on the fault-proneness of a software system. Similarly, Saboury et al. found a relationship between anti-pattern occurrences and fault-proneness, using heuristic to identify fault-fixing commits and fault-inducing changes. However, recent studies question the accuracy of heuristics, and thus the validity of empirical studies that leverage it. Hence, in this work, we would like to investigate to what extent the results of empirical studies using heuristics to identify bug fix commits are affected by the limitations of the heuristics based approach using manually validated bug fix commits as a ground truth. In particular, we conduct a differentiated replication of the work by Khomh et al. We particularly focused on the impact of anti-patterns on fault-proneness as it is the only dependent variable that may be affected by noise in the collected faults data. In our differentiated replication study, (1) we expanded the number of subject systems from 5 to 38, (2) utilized a manually validated dataset of bug-fixing commits from the work of Herbold et al., and (3) answered research questions from Khomh et al., that are related to the relationship between anti-pattern occurrences and fault-proneness. (4) We added an additional research question to investigate if combining results from several heuristic-based approaches could help reduce the impact of noise. Our findings show that the impact of the noise generated by the automatic algorithm heuristic based is negligible for the studied subject systems; meaning that the reported relation observed on noisy data still holds on the clean data. However, we also observed that combining results from several heuristic based approaches do not reduce this noise, quite the contrary.

2022-10-02

2022 IEEE 22nd International Working Conference on Source Code Analysis and Manipulation (SCAM) (publié)

doi.org

Uncertainty-Driven Active Vision for Implicit Scene Reconstruction

Edward J. Smith

Michal Drozdzal

D. Nowrouzezahrai

David Meger

Adriana Romero

2022-10-02

ArXiv (prépublication)

doi.org