Publications

Predicting Grokking Long Before it Happens: A look into the loss landscape of models which grok
Tikeng Notsawo Pascal Junior
Pascal Notsawo
Hattie Zhou
Mohammad Pezeshki
Irina Rish
Guillaume Dumas
2024-03-04
ICLR.cc/2024/Workshop/ME-FoMo (poster)
doi.org
openreview.net
Self-evaluation and self-prompting to improve the reliability of LLMs
Alexandre Piché
Aristides Milios
Dzmitry Bahdanau
Chris Pal
In order to safely deploy Large Language Models (LLMs), they must be capable of dynamically adapting their behavior based on their level of … (see more)knowledge and uncertainty associated with specific topics. This adaptive behavior, which we refer to as self-restraint, is non-trivial to teach since it depends on the internal knowledge of an LLM. By default, LLMs are trained to maximize the next token likelihood which does not teach the model to modulate its answer based on its level of uncertainty. In order to learn self-restraint, we devise a simple objective that can encourage the model to produce generation that the model is confident in. To optimize this objective, we introduce ReSearch, an iterative search algorithm based on self-evaluation and self-prompting. Our method results in fewer hallucinations overall, both for known and unknown topics, as the model learns to selectively restrain itself. In addition, our method elegantly incorporates the ability to decline, when the model assesses that it cannot provide a response without a high proportion of hallucination.
2024-03-04
ICLR.cc/2024/Workshop/SeT_LLM (published)
openreview.net
openreview.net
Self-evaluation and self-prompting to improve the reliability of LLMs
Alexandre Piché
Aristides Milios
Dzmitry Bahdanau
Chris Pal
In order to safely deploy Large Language Models (LLMs), they must be capable of dynamically adapting their behavior based on their level of … (see more)knowledge and uncertainty associated with specific topics. This adaptive behavior, which we refer to as self-restraint, is non-trivial to teach since it depends on the internal knowledge of an LLM. By default, LLMs are trained to maximize the next token likelihood which does not teach the model to modulate its answer based on its level of uncertainty. In order to learn self-restraint, we devise a simple objective that can encourage the model to produce generation that the model is confident in. To optimize this objective, we introduce ReSearch, an iterative search algorithm based on self-evaluation and self-prompting. Our method results in fewer hallucinations overall, both for known and unknown topics, as the model learns to selectively restrain itself. In addition, our method elegantly incorporates the ability to decline, when the model assesses that it cannot provide a response without a high proportion of hallucination.
2024-03-04
ICLR.cc/2024/Workshop/SeT_LLM (published)
openreview.net
openreview.net
Structure-Informed Protein Language Model
Zuobai Zhang
Jiarui Lu
Vijil Chenthamarakshan
Aurelie Lozano
Payel Das
Jian Tang
Protein language models are a powerful tool for learning protein representations through pre-training on vast protein sequence datasets. Ho… (see more)wever, traditional protein language models lack explicit structural supervision, despite its relevance to protein function. To address this issue, we introduce the integration of remote homology detection to distill structural information into protein language models without requiring explicit protein structures as input. We evaluate the impact of this structure-informed training on downstream protein function prediction tasks. Experimental results reveal consistent improvements in function annotation accuracy for EC number and GO term prediction. Performance on mutant datasets, however, varies based on the relationship between targeted properties and protein structures. This underscores the importance of considering this relationship when applying structure-aware training to protein function prediction tasks. Code and model weights will be made available upon acceptance.
2024-03-04
ICLR.cc/2024/Workshop/GEM (poster)
openreview.net
openreview.net
On the Scalability of GNNs for Molecular Graphs
Maciej Sypetkowski
Frederik Wenkel
Farimah Poursafaei
Nia Dickson
Karush Suri
Philip Fradkin
Dominique Beaini
Scaling deep learning models has been at the heart of recent revolutions in language modelling and image generation. Practitioners have obse… (see more)rved a strong relationship between model size, dataset size, and performance. However, structure-based architectures such as Graph Neural Networks (GNNs) are yet to show the benefits of scale mainly due to the lower efficiency of sparse operations, large data requirements, and lack of clarity about the effectiveness of various architectures. We address this drawback of GNNs by studying their scaling behavior. Specifically, we analyze message-passing networks, graph Transformers, and hybrid architectures on the largest public collection of 2D molecular graphs. For the first time, we observe that GNNs benefit tremendously from the increasing scale of depth, width, number of molecules, number of labels, and the diversity in the pretraining datasets, resulting in a 30.25% improvement when scaling to 1 billion parameters and 28.98% improvement when increasing size of dataset to eightfold. We further demonstrate strong finetuning scaling behavior on 38 tasks, outclassing previous large models. We hope that our work paves the way for an era where foundational GNNs drive pharmaceutical drug discovery.
2024-03-04
ICLR.cc/2024/Workshop/DPFM (poster)
openreview.net
openreview.net
Towards DNA-Encoded Library Generation with GFlowNets
Michał Koziarski
Mohammed Abukalam
Vedant Shah
Louis Vaillancourt
Doris Alexandra Schuetz
Moksh J. Jain
Almer M. van der Sloot
Mathieu Bourgey
Anne Marinier
Yoshua Bengio
2024-03-04
ICLR.cc/2024/Workshop/GEM (poster)
doi.org
openreview.net
Communicating Study Design Trade-offs in Software Engineering
Martin P. Robillard
Deeksha M. Arya
Neil Ernst
Jin Guo
Maxime Lamothe
Mathieu Nassif
Nicole Novielli
Alexander Serebrenik
Igor Steinmacher
Klaas-Jan Stol
2024-03-02
ACM Transactions on Software Engineering and Methodology (published)
doi.org
A Compositional Typed Semantics for Universal Dependencies
Laurestine Bradford
Timothy John O'donnell
Siva Reddy
2024-03-02
ArXiv (preprint)
doi.org
arxiv.org
Harmony in Diversity: Merging Neural Networks with Canonical Correlation Analysis
Stefan Horoi
Albert Manuel Orozco Camacho
Eugene Belilovsky
Guy Wolf
Ensembling multiple models enhances predictive performance by utilizing the varied learned features of the different models but incurs signi… (see more)ficant computational and storage costs. Model fusion, which combines parameters from multiple models into one, aims to mitigate these costs but faces practical challenges due to the complex, non-convex nature of neural network loss landscapes, where learned minima are often separated by high loss barriers. Recent works have explored using permutations to align network features, reducing the loss barrier in parameter space. However, permutations are restrictive since they assume a one-to-one mapping between the different models' neurons exists. We propose a new model merging algorithm, CCA Merge, which is based on Canonical Correlation Analysis and aims to maximize the correlations between linear combinations of the model features. We show that our method of aligning models leads to better performances than past methods when averaging models trained on the same, or differing data splits. We also extend this analysis into the harder many models setting where more than 2 models are merged, and we find that CCA Merge works significantly better in this setting than past methods.
2024-03-02
ICLR.cc/2024/Workshop/Re-Align (poster)
openreview.net
openreview.net
Latent Idiom Recognition for a Minimalist Functional Array Language Using Equality Saturation
Jonathan Van Der Cruysse
Christophe Dubach
Accelerating programs is typically done by recognizing code idioms matching high-performance libraries or hardware interfaces. However, reco… (see more)gnizing such idioms automatically is challenging. The idiom recognition machinery is difficult to write and requires expert knowledge. In addition, slight variations in the input program might hide the idiom and defeat the recognizer. This paper advocates for the use of a minimalist functional array language supporting a small, but expressive, set of operators. The minimalist design leads to a tiny sets of rewrite rules, which encode the language semantics. Crucially, the same minimalist language is also used to encode idioms. This removes the need for hand-crafted analysis passes, or for having to learn a complex domain-specific language to define the idioms. Coupled with equality saturation, this approach is able to match the core functions from the BLAS and PyTorch libraries on a set of computational kernels. Compared to reference C kernel implementations, the approach produces a geometric mean speedup of 1.46× for C programs using BLAS, when generating such programs from the high-level minimalist language.
2024-03-02
2024 IEEE/ACM International Symposium on Code Generation and Optimization (CGO) (published)
doi.org
arxiv.org
Learning and Aligning Structured Random Feature Networks
Vivian White
Muawiz Sajjad Chaudhary
Guy Wolf
Guillaume Lajoie
Kameron Decker Harris
Artificial neural networks (ANNs) are considered ``black boxes'' due to the difficulty of interpreting their learned weights. While choosin… (see more)g the best features is not well understood, random feature networks (RFNs) and wavelet scattering ground some ANN learning mechanisms in function space with tractable mathematics. Meanwhile, the genetic code has evolved over millions of years, shaping the brain to devlop variable neural circuits with reliable structure that resemble RFNs. We explore a similar approach, embedding neuro-inspired, wavelet-like weights into multilayer RFNs. These can outperform scattering and have kernels that describe their function space at large width. We build learnable and deeper versions of these models where we can optimize separate spatial and channel covariances of the convolutional weight distributions. We find that these networks can perform comparatively with conventional ANNs while dramatically reducing the number of trainable parameters. Channel covariances are most influential, and both weight and activation alignment are needed for classification performance. Our work outlines how neuro-inspired configurations may lead to better performance in key cases and offers a potentially tractable reduced model for ANN learning.
2024-03-02
ICLR.cc/2024/Workshop/Re-Align (poster)
openreview.net
openreview.net
Learning and Aligning Structured Random Feature Networks
Vivian White
Muawiz Sajjad Chaudhary
Guy Wolf
Guillaume Lajoie
Kameron Decker Harris
Artificial neural networks (ANNs) are considered "black boxes'' due to the difficulty of interpreting their learned weights. While choosing… (see more) the best features is not well understood, random feature networks (RFNs) and wavelet scattering ground some ANN learning mechanisms in function space with tractable mathematics. Meanwhile, the genetic code has evolved over millions of years, shaping the brain to develop variable neural circuits with reliable structure that resemble RFNs. We explore a similar approach, embedding neuro-inspired, wavelet-like weights into multilayer RFNs. These can outperform scattering and have kernels that describe their function space at large width. We build learnable and deeper versions of these models where we can optimize separate spatial and channel covariances of the convolutional weight distributions. We find that these networks can perform comparatively with conventional ANNs while dramatically reducing the number of trainable parameters. Channel covariances are most influential, and both weight and activation alignment are needed for classification performance. Our work outlines how neuro-inspired configurations may lead to better performance in key cases and offers a potentially tractable reduced model for ANN learning.
2024-03-02
ICLR.cc/2024/Workshop/Re-Align (poster)
openreview.net
openreview.net