Machine translation, multiagent reinforcement learning: what Amii researchers are presenting at AAAI 2022

Amii is excited to showcase the work done by our researchers being featured at the 36th annual AAAI Conference on Artificial Intelligence, held online from February 22 - March 1, 2022.

The AAAI conference aims to promote research into artificial intelligence and to offer the opportunity for scientific exchange between AI researchers, practitioners, and engineers in affiliated disciplines. This year’s conference will include student abstracts, poster sessions, speakers, workshops, as well as exhibit and competition programs.

The AAAI conference is one of the top five AI and ML conferences in the world, based on Guide2Research’s rankings of its h-index and Impact Score values.

This year, accepted papers submitted by Amii researchers touch on topics such as improvements to AI language translation and text generation, new approaches to multiagent reinforcement learning, and new frameworks for AI interpretation of medical imaging data.

Check out the full list of the accepted papers from Amii researchers, as well as their other work at AAAI.

Accepted Papers

What Can We Learn Even from the Weakest? Learning Sketches for Programmatic Strategies

Leandro C. Medeiros, David S. Aleixo, Levi H. S. Lelis

Abstract: In this paper we show that behavioral cloning can be used to learn effective sketches of programmatic strategies. We show that even the sketches learned by cloning the behavior of weak players can help the synthesis of programmatic strategies. This is because even weak players can provide helpful information, e.g., that a player must choose an action in their turn of the game. If behavioral cloning is not employed, the synthesizer needs to learn even the most basic information by playing the game, which can be computationally expensive. We demonstrate empirically the advantages of our sketch-learning approach with simulated annealing and UCT synthesizers. We evaluate our synthesizers in the games of Can’t Stop and MicroRTS. The sketch-based synthesizers are able to learn stronger programmatic strategies than their original counterparts. Our synthesizers generate strategies of Can’t Stop that defeat a traditional programmatic strategy for the game. They also synthesize strategies that defeat the best performing method from the latest MicroRTS competition.

Non-Autoregressive Translation with Layer-Wise Prediction and Deep Supervision

Chenyang Huang, Hao Zhou, Osmar R. Zaïane, Lili Mou, Lei Li

Abstract: How do we perform efficient inference while retaining high translation quality? Existing neural machine translation models, such as Transformer, achieve high performance, but they decode words one by one, which is inefficient. Recent non-autoregressive translation models speed up the inference, but their quality is still inferior. In this work, we propose DSLP, a highly efficient and high-performance model for machine translation. The key insight is to train a non-autoregressive Transformer with Deep Supervision and feed additional Layer-wise Predictions. We conducted extensive experiments on four translation tasks (both directions of WMT'14 EN-DE and WMT'16 EN-RO). Results show that our approach consistently improves the BLEU scores compared with respective base models. Specifically, our best variant outperforms the autoregressive model on three translation tasks, while being 14.8 times more efficient in inference.

Search and Learn: Improving Semantic Coverage for Data-to-Text Generation

Shailza Jolly, Zi Xuan Zhang, Andreas Dengel, Lili Mou

Abstract: Data-to-text generation systems aim to generate text descriptions based on input data (often represented in the tabular form). A typical system uses huge training samples for learning the correspondence between tables and texts. However, large training sets are expensive to obtain, limiting the applicability of these approaches in real-world scenarios. In this work, we focus on few-shot data-to-text generation. We observe that, while fine-tuned pretrained language models may generate plausible sentences, they suffer from the low semantic coverage problem in the few-shot setting. In other words, important input slots tend to be missing in the generated text. To this end, we propose a search-and-learning approach that leverages pretrained language models but inserts the missing slots to improve the semantic coverage. We further fine-tune our system based on the search results to smooth out the search noise, yielding better-quality text and improving inference efficiency to a large extent. Experiments show that our model achieves high performance on E2E and WikiBio datasets. Especially, we cover 98.35% of input slots on E2E, largely alleviating the low coverage problem.

Generalized Equivariance and Preferential Labeling for GNN Node Classification

Zeyu Sun, Wenjie Zhang, Lili Mou, Qihao Zhu, Yingfei Xiong, Lu Zhang

Abstract: Existing graph neural networks (GNNs) largely rely on node embeddings, which represent a node as a vector by its identity, type, or content. However, graphs with unattributed nodes widely exist in real-world applications (e.g., anonymized social networks). Previous GNNs either assign random labels to nodes (which introduces artefacts to the GNN) or assign one embedding to all nodes (which fails to explicitly distinguish one node from another). Further, when these GNNs are applied to unattributed node classification problems, they have an undesired equivariance property, which are fundamentally unable to address the data with multiple possible outputs. In this paper, we analyze the limitation of existing approaches to node classification problems. Inspired by our analysis, we propose a generalized equivariance property and a Preferential Labeling technique that satisfies the desired property asymptotically. Experimental results show that we achieve high performance in several unattributed node classification tasks.

Decentralized Mean Field Games

Sriram Ganapathi Subramanian, Matthew E. Taylor, Mark Crowley, Pascal Poupart

Abstract: Multiagent reinforcement learning algorithms have not been widely adopted in large scale environments with many agents as they often scale poorly with the number of agents. Using mean field theory to aggregate agents has been proposed as a solution to this problem. However, almost all previous methods in this area make a strong assumption of a centralized system where all the agents in the environment learn the same policy and are effectively indistinguishable from each other. In this paper, we relax this assumption about indistinguishable agents and propose a new mean field system known as Decentralized Mean Field Games, where each agent can be quite different from others. All agents learn independent policies in a decentralized fashion, based on their local observations. We define a theoretical solution concept for this system and provide a fixed point guarantee for a Q-learning based algorithm in this system. A practical consequence of our approach is that we can address a `chicken-and-egg' problem in empirical mean field reinforcement learning algorithms. Further, we provide Q-learning and actor-critic algorithms that use the decentralized mean field learning approach and give stronger performances compared to common baselines in this area. In our setting, agents do not need to be clones of each other and learn in a fully decentralized fashion. Hence, for the first time, we show the application of mean field learning methods in fully competitive environments, large-scale continuous action space environments, and other environments with heterogeneous agents. Importantly, we also apply the mean field method in a ride-sharing problem using a real-world dataset. We propose a decentralized solution to this problem, which is more practical than existing centralized training methods.

Learning Expected Emphatic Traces for Deep RL

Ray Jiang, Shangtong Zhang, Veronica Chelu, Adam White, Hado van Hasselt

Abstract: Off-policy sampling and experience replay are key for improving sample efficiency and scaling model-free temporal difference learning methods. When combined with function approximation, such as neural networks, this combination is known as the deadly triad and is potentially unstable. Recently, it has been shown that stability and good performance at scale can be achieved by combining emphatic weightings and multi-step updates. This approach, however, is generally limited to sampling complete trajectories in order, to compute the required emphatic weighting. In this paper we investigate how to combine emphatic weightings with non-sequential, off-line data sampled from a replay buffer. We develop a multi-step emphatic weighting that can be combined with replay, and a time-reversed n-step TD learning algorithm to learn the required emphatic weighting. We show that these state weightings reduce variance compared with prior approaches, while providing convergence guarantees. We tested the approach at scale on Atari 2600 video games, and observed that the new X-ETD(n) agent improved over baseline agents, highlighting both the scalability and broad applicability of our approach.

UCTransNet: Rethinking the Skip Connections in U-Net from a Channel-Wise Perspective with Transformer

Haonan Wang, Peng Cao, Jiaqi Wang, Osmar R. Zaiane

Abstract: Most recent semantic segmentation methods adopt a U-Net framework with an encoder-decoder architecture. It is still challenging for U-Net with a simple skip connection scheme to model the global multi-scale context: 1) Not each skip connection setting is effective due to the issue of incompatible feature sets of encoder and decoder stage, even some skip connection negatively influence the segmentation performance; 2) The original U-Net is worse than the one without any skip connection on some datasets. Based on our findings, we propose a new segmentation framework, named UCTransNet (with a proposed CTrans module in U-Net), from the channel perspective with attention mechanism. Specifically, the CTrans module is an alternate of the U-Net skip connections, which consists of a sub-module to conduct the multi-scale Channel Cross fusion with Transformer (named CCT) and a sub-module Channel-wise Cross-Attention (named CCA) to guide the fused multi-scale channel-wise information to effectively connect to the decoder features for eliminating the ambiguity. Hence, the proposed connection consisting of the CCT and CCA is able to replace the original skip connection to solve the semantic gaps for an accurate automatic medical image segmentation. The experimental results suggest that our UCTransNet produces more precise segmentation performance and achieves consistent improvements over the state-of-the-art for semantic segmentation across different datasets and conventional architectures involving transformer or U-shaped framework.

The Perils of Learning Before Optimizing

Chris Cameron, Jason Hartford, Taylor Lundy, Kevin Leyton-Brown

Abstract: Formulating real-world optimization problems often begins with making predictions from historical data (e.g., an optimizer that aims to recommend fast routes relies upon travel-time predictions). Typically, learning the prediction model used to generate the optimization problem and solving that problem are performed in two separate stages. Recent work has showed how such prediction models can be learned end-to-end by differentiating through the optimization task. Such methods often yield empirical improvements, which are typically attributed to end-to-end making better error tradeoffs than the standard loss function used in a two-stage solution. We refine this explanation and more precisely characterize when end-to-end can improve performance. When prediction targets are stochastic, a two-stage solution must make an a priori choice about which statistics of the target distribution to model-we consider expectations over prediction targets-while an end-to-end solution can make this choice adaptively. We show that the performance gap between a two-stage and end-to-end approach is closely related to the price of correlation concept in stochastic optimization and show the implications of some existing POC results for the predict-then-optimize problem. We then consider a novel and particularly practical setting, where multiple prediction targets are combined to obtain each of the objective function's coefficients. We give explicit constructions where (1) two-stage performs unboundedly worse than end-to-end; and (2) two-stage is optimal. We use simulations to experimentally quantify performance gaps and identify a wide range of real-world applications from the literature whose objective functions rely on multiple prediction targets, suggesting that end-to-end learning could yield significant improvements.

Diversity and Inclusion Events

Queer in AI

Raj Korpan, Danica Sutherland

Queer in AI’s presence at AAAI 2022 aims to create a safe and inclusive casual networking and socializing space for LGBTQIA+ individuals and allies involved with AI. We aim to create a community space where attendees can connect with each other, bond over shared experiences, and learn from each individual’s unique insights into AI, queerness, and beyond! We will have two events at AAAI: A social event, to bring the community together. A speaker will reflect on the diversity and inclusion of the AI community, followed by an informal networking session. The event will be free and open to all; see the website for registration info. We will also host a mentorship session for undergraduate and junior grad students, where speakers will talk about their journey since undergrad, a Q&A session, and break-out groups to pair students with a more senior member of the community.

Amii researchers have also served in the organization of the conference:

Nathan Sturtevant - Senior Member Track Cochair