Publications

Generalizing in the Real World with Representation Learning
Tegan Maharaj
2022-10-17
ArXiv (prépublication)
doi.org
arxiv.org
Social isolation and the brain in the pandemic era
Danilo Bzdok
Robin I. M. Dunbar
2022-10-17
Nature Human Behaviour (publié)
doi.org
Adapting Triplet Importance of Implicit Feedback for Personalized Recommendation
Haolun Wu
Chen Ma
Yingxue Zhang
Xue Liu
Ruiming Tang
Mark J. Coates
2022-10-16
Proceedings of the 31st ACM International Conference on Information & Knowledge Management (publié)
doi.org
arxiv.org
Better Modeling the Programming World with Code Concept Graphs-augmented Multi-modal Learning
Martin Weyssow
Houari Sahraoui
Bang Liu
The progress made in code modeling has been tremendous in recent years thanks to the design of natural language processing learning approach… (voir plus)es based on state-of-the-art model architectures. Nevertheless, we believe that the current state-of-the-art does not focus enough on the full potential that data may bring to a learning process in software engineering. Our vision articulates on the idea of leveraging multi-modal learning approaches to modeling the programming world. In this paper, we investigate one of the underlying idea of our vision whose objective based on concept graphs of identifiers aims at leveraging high-level relationships between domain concepts manipulated through particular language constructs. In particular, we propose to enhance an existing pretrained language model of code by joint-learning it with a graph neural network based on our concept graphs. We conducted a preliminary evaluation that shows gain of effectiveness of the models for code search using a simple joint-learning method and prompts us to further investigate our research vision.
2022-10-16
Proceedings of the ACM/IEEE 44th International Conference on Software Engineering: New Ideas and Emerging Results (publié)
doi.org
arxiv.org
Identification of out-of-distribution cases of CNN using class-based surprise adequacy
Mira Marhaba
Ettore Merlo
Foutse Khomh
Giuliano Antoniol
Machine learning is vulnerable to possible incorrect classification of cases that are out of the distribution observed during training and c… (voir plus)alibration
2022-10-16
Proceedings of the 1st International Conference on AI Engineering: Software Engineering for AI (publié)
doi.org
OptEmbed: Learning Optimal Embedding Table for Click-through Rate Prediction
Fuyuan Lyu
Xing Tang
Hao Zhu
Huifeng Guo
Yingxue Zhang
Ruiming Tang
Xue Liu
Click-through rate (CTR) prediction model usually consists of three components: embedding table, feature interaction layer, and classifier. … (voir plus)Learning embedding table plays a fundamental role in CTR prediction from the view of the model performance and memory usage. The embedding table is a two-dimensional tensor, with its axes indicating the number of feature values and the embedding dimension, respectively. To learn an efficient and effective embedding table, recent works either assign various embedding dimensions for feature fields and reduce the number of embeddings respectively or mask the embedding table parameters. However, all these existing works cannot get an optimal embedding table. On the one hand, various embedding dimensions still require a large amount of memory due to the vast number of features in the dataset. On the other hand, decreasing the number of embeddings usually suffers from performance degradation, which is intolerable in CTR prediction. Finally, pruning embedding parameters will lead to a sparse embedding table, which is hard to be deployed. To this end, we propose an optimal embedding table learning framework OptEmbed, which provides a practical and general method to find an optimal embedding table for various base CTR models. Specifically, we propose pruning the redundant embeddings regarding corresponding features' importance by learnable pruning thresholds. Furthermore, we consider assigning various embedding dimensions as one single candidate architecture. To efficiently search the optimal embedding dimensions, we design a uniform embedding dimension sampling scheme to equally train all candidate architectures, meaning architecture-related parameters and learnable thresholds are trained simultaneously in one supernet. We then propose an evolution search method based on the supernet to find the optimal embedding dimensions for each field. Experiments on public datasets show that OptEmbed can learn a compact embedding table which can further improve the model performance.
2022-10-16
Proceedings of the 31st ACM International Conference on Information & Knowledge Management (publié)
doi.org
arxiv.org
Using Graph Algorithms to Pretrain Graph Completion Transformers
Jonathan Pilault
Mikhail Galkin
Bahare Fatemi
Perouz Taslakian
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
Synthetic data as an enabler for machine learning applications in medicine
Jean-Francois Rajotte
Robert Bergen
David L Buckeridge
Khaled El Emam
Raymond Ng
Elissa Strome
2022-10-12
iScience (publié)
doi.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
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