Canada

We consider algorithms for learning reward functions from human preferences over pairs of trajectory segments, as used in reinforcement learning from human feedback (RLHF). Most recent work assumes that human preferences are generated based only upon the reward accrued within those segments, or their \textit{partial return}. Recent work casts doubt on the validity of this assumption, proposing an alternative preference model based upon \textit{regret}. We investigate the consequences of assuming preferences are based upon partial return when they actually arise from regret. We argue that the learned function is an approximation of the optimal advantage function, $\widehat{A^*_r}$, \textit{not} a reward function. We find that if a specific pitfall is addressed, this incorrect assumption is not particularly harmful, resulting in a highly shaped reward function. Nonetheless, this incorrect usage of $\widehat{A^*_r}$ is less desirable than the appropriate and simpler approach of greedy maximization of $\widehat{A^*_r}$. From the perspective of the regret preference model, we also provide a clearer interpretation of fine tuning contemporary large language models with RLHF. This paper overall provides insight regarding why learning under the partial return preference model tends to work so well in practice, despite it conforming poorly to how humans give preferences.

AAAI 2024

Learning Optimal Advantage from Preferences and Mistaking It for Reward

machine learning (ml) -> ml: reinforcement learning

machine learning (ml) -> ml: imitation learning & inverse reinforcement learning

humans and ai(hai) -> hai: learning human values and preferences

technical paper

We are pleased to announce the Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI-24), which will be held in Vancouver, British Columbia at the Vancouver Convention Centre – West Building from 20-27 February, 2024.

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-24 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.

We expect for AAAI-24 to be an in-person conference – one author of all accepted papers will be expected to present work in person unless there are exceptional circumstances that prevent this.<br><br><br><br>

In order to access the AAAI-24 event page you need to register [here](https://aaai.org/aaai-conference/registration/)

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. 

Summarizing sequential data with serial episodes allows non-trivial insight into the data generating process. Existing methods penalize gaps in pattern occurrences equally, regardless of where in the pattern these occur. This results in a strong bias against patterns with long inter-event delays, and in addition that regularity in terms of delays is not rewarded or discovered---even though both aspects provide key insight.
In this paper we tackle both these problems by explicitly modeling inter-event delay distributions. That is, we are not only interested in discovering the patterns, but also in describing how many times steps typically occur between their individual events. We formalize the problem in terms of the Minimum Description Length principle, by which we say the best set of patterns is the one that compresses the data best. The resulting optimization problem does not lend itself to exact optimization, and hence we propose Hopper to heuristically mine high quality patterns. Extensive experiments show that Hopper efficiently recovers the ground truth, discovers meaningful patterns from real-world data, and outperforms existing methods in discovering long-delay patterns.

Discovering Sequential Patterns with Predictable Inter-event Delays

Graph Neural Networks (GNNs), despite achieving remarkable performance across different tasks, are theoretically bounded by the 1-Weisfeiler-Lehman test, resulting in limitations in terms of graph expressivity. Even though prior works on topological higher-order GNNs overcome that boundary, these models often depend on assumptions about sub-structures of graphs. Specifically, topological GNNs leverage the prevalence of cliques, cycles, and rings to enhance the message-passing procedure. Our study presents a novel perspective by focusing on simple paths within graphs during the topological message-passing process, thus liberating the model from restrictive inductive biases. We prove that by lifting graphs to path complexes, our model can generalize the existing works on topology while inheriting several theoretical results on simplicial complexes and regular cell complexes. Without making prior assumptions about graph sub-structures, our method outperforms earlier works in other topological domains and achieves state-of-the-art results on various benchmarks.

Weisfeiler and Lehman Go Paths: Learning Topological Features via Path Complexes

Offline Goal-Conditioned Reinforcement Learning (Offline GCRL) is an important problem in RL that focuses on acquiring diverse goal-oriented skills solely from pre-collected behavior datasets. 
In this setting, the reward feedback is typically absent except when the goal is achieved, 
which makes it difficult to learn policies especially from a finite dataset of suboptimal behaviors.
In addition, realistic scenarios involve long-horizon planning, which necessitates the 
extraction of useful skills within sub-trajectories.
Recently, the conditional diffusion model has been shown to be a promising approach to 
generate high-quality long-horizon plans for RL. 
However, their
practicality for the goal-conditioned setting is still limited due to a number of technical assumptions
made by the methods.
In this paper, we propose \textit{SSD (Sub-trajectory Stitching with Diffusion)}, 
a model-based offline GCRL method that leverages the conditional diffusion model to address these limitations. 
In summary, we use the diffusion model that generates future plans conditioned on the target goal and value, 
with the target value estimated from the goal-relabeled offline dataset. % to address the issue of long-horizon planning. 
We report state-of-the-art performance in the standard benchmark set of GCRL tasks, and 
demonstrate the capability to successfully stitch the segments of suboptimal trajectories in the offline data to generate high-quality plans.

Stitching Sub-trajectories with Conditional Diffusion Model for Goal-Conditioned Offline RL | VIDEO

Taking incompatible multiple drugs together may cause adverse interactions and side effects on the body. Accurate prediction of drug-drug interaction (DDI) events is essential for avoiding this issue. Recently, various artificial intelligence-based approaches have been proposed for predicting DDI events. However, DDI events are associated with complex relationships and mechanisms among drugs, targets, enzymes, transporters, molecular structures, etc. Existing approaches either partially or loosely consider these relationships and mechanisms by a non-end-to-end learning framework, resulting in sub-optimal feature extractions and fusions for prediction. Different from them, this paper proposes a Multimodal Knowledge Graph Fused End-to-end Neural Network (MKGFENN) that consists of two main parts: multimodal knowledge graph (MKG) and fused end-to-end neural network (FENN). First, MKG is constructed by comprehensively exploiting DDI events-associated relationships and mechanisms from four knowledge graphs of drugs-chemical entities, drug-substructures, drugs-drugs, and molecular structures. Correspondingly, a four channels graph neural network is designed to extract high-order and semantic features from MKG. Second, FENN designs a multi-layer perceptron to fuse the extracted features by end-to-end learning. With such designs, the feature extractions and fusions of DDI events are guaranteed to be comprehensive and optimal for prediction. Through extensive experiments on real drug datasets, we demonstrate that MKG-FENN exhibits high accuracy and significantly outperforms state-of-the-art models in predicting DDI events. The source code and supplementary file of this article are available on: https://github.com/wudi1989/MKG-FENN.

MKG-FENN: A Multimodal Knowledge Graph Fused End-to-End Neural Network for Accurate Drug–Drug Interaction Prediction

Graph-based multimedia data clustering has attracted much attention due to the impressive clustering performance for arbitrarily shaped multimedia data. However, existing graph-based clustering methods need post-processing to get labels for multimedia data with high computational complexity. Moreover, it is sub-optimal for label learning due to the fact that they exploit the complementary information embedded in data with different types pixel by pixel. To handle these problems, we present a novel label learning model with good interpretability for clustering. To be specific, our model decomposes anchor graph into the products of two matrices with orthogonal non-negative constraint to directly get soft label without any post-processing, which remarkably reduces the computational complexity. To well exploit the complementary information embedded in multimedia data, we introduce tensor Schatten p-norm regularization on the label tensor which is composed of soft labels of multimedia data. The solution can be obtained by iteratively optimizing four decoupled sub-problems, which can be solved more efficiently with good convergence. Experimental results on various datasets demonstrate the efficiency of our model.

Tensorized Label Learning on Anchor Graph

Self-interpretable graph learning methods provide insights to unveil the black-box nature of GNNs by providing predictions with built-in explanations. However, current works suffer from performance degradation compared to GNNs trained without built-in explanations. We argue the main reason is that they fail to generate explanations satisfying both sufficiency and necessity, and the biased explanations further hurt GNNs' performance. In this work, we propose a novel framework for generating SUfficient aNd NecessarY explanations (SUNNY-GNN for short) that benefit GNNs' predictions. The key idea is to conduct augmentations by structurally perturbing given explanations and employ a contrastive loss to guide the learning of explanations toward sufficiency and necessity directions. SUNNY-GNN introduces two coefficients to generate hard and reliable contrastive samples. We further extend SUNNY-GNN to heterogeneous graphs. Empirical results on various GNNs and real-world graphs show that SUNNY-GNN yields accurate predictions and faithful explanations, outperforming the state-of-the-art methods by improving 3.5% prediction accuracy and 13.1% explainability fidelity on average. Our code and data are available at https://github.com/SJTU-Quant/SUNNY-GNN.

Self-Interpretable Graph Learning with Sufficient and Necessary Explanations

Multi-spectral object Re-identification (ReID) aims to retrieve specific objects by leveraging complementary information from different image spectra. It delivers great advantages over traditional single-spectral ReID in complex visual environment. However, the significant distribution gap among different image spectra poses great challenges for effective multi-spectral feature representations. In addition, most of current Transformer-based ReID methods only utilize the global feature of class tokens to achieve the holistic retrieval, ignoring the local discriminative ones. To address the above issues, we step further to utilize all the tokens of Transformers and propose a cyclic token permutation framework for multi-spectral object ReID, dubbled TOP-ReID. More specifically, we first deploy a multi-stream deep network based on vision Transformers to preserve distinct information from different image spectra. Then, we propose a Token Permutation Module (TPM) for cyclic multi-spectral feature aggregation. It not only facilitates the spatial feature alignment across different image spectra, but also allows the class token of each spectrum to perceive the local details of other spectra. Meanwhile, we propose a Complementary Reconstruction Module (CRM), which introduces dense token-level reconstruction constraints to reduce the distribution gap across different image spectra. With the above modules, our proposed framework can generate more discriminative multi-spectral features for robust object ReID. Extensive experiments on three ReID benchmarks (i.e., RGBNT201, RGBNT100 and MSVR310) verify the effectiveness of our methods. The code is available at https://github.com/924973292/TOP-ReID.

TOP-ReID: Multi-Spectral Object Re-identification with Token Permutation

Light field microscopy is a high-speed 3D imaging technique that records the light field from multiple angles by the microlens array(MLA), thus allowing us to obtain information about the light source from a single image only. For the fundamental problem of neuron localization, we improve the method of combining depth-dependent dictionary with sparse coding in this paper. In order to obtain higher localization accuracy and good noise immunity, we propose an inertial proximal gradient acceleration algorithm with dry friction, FAST-IPGDF. By preventing falling into a local minimum, our algorithm achieves better convergence and converges quite fast, which improves the speed and accuracy of obtaining the locolization of the light source based on the matching depth of epipolar plane images (EPI). We demonstrate the effectiveness of the algorithm for localizing non-scattered fluorescent beads in both noisy and non-noisy environments. The experimental results show that our method can achieve simultaneous localization of multiple point sources and effective localization in noisy environments. Compared to existing studies, our method shows significant improvements in both localization accuracy and speed.

Inertial Algorithm with Dry Fraction and Convolutional Sparse Coding for 3D Localization with Light Field Microscopy

Augmented Reality (AR) devices, emerging as prominent mobile interaction platforms, face challenges in user safety, particularly concerning oncoming vehicles. While some solutions leverage onboard camera arrays, these cameras often have limited field-of-view (FoV) with front or downward perspectives. Addressing this, we propose a new out-of-view semantic segmentation task and Segment Beyond View (SBV), a novel audio-visual semantic segmentation method. SBV supplements the visual modality, which miss the information beyond FoV, with the auditory information using a teacher-student distillation model (Omni2Ego). The model consists of a vision teacher utilising panoramic information, an auditory teacher with 8-channel audio, and an audio-visual student that takes views with limited FoV and binaural audio as input and produce semantic segmentation for objects outside FoV. SBV outperforms existing models in comparative evaluations and shows a consistent performance across varying FoV ranges and in monaural audio settings.

Segment beyond View: Handling Partially Missing Modality for Audio-Visual Semantic Segmentation

Training Generative Adversarial Networks (GAN) to generate high-quality images typically requires large datasets. Network pruning during training has recently emerged as a significant advancement for data-efficient GAN. However, simple and straightforward pruning can lead to the risk of losing key information, resulting in suboptimal results due to GAN’s competitive dynamics between generator (G) and discriminator (D). Addressing this, we present RG-GAN, a novel approach that marks the first incorporation of dynamic weight regeneration and pruning in GAN training to improve the quality of the generated samples, even with limited data. Specifically, RG-GAN initiates layer-wise dynamic pruning by removing less important weights to the quality of the generated images. While pruning enhances efficiency, excessive sparsity within layers can pose a risk of model collapse. To mitigate this issue, RG-GAN applies a dynamic regeneration method to reintroduce specific weights when they become important, ensuring a balance between sparsity and image quality. Though effective, the sparse network achieved through this process might eliminate some weights important to the combined G and D performance, a crucial aspect for achieving stable and effective GAN training. RG-GAN addresses this loss of weights by integrating learned sparse network weights back into the dense network at the previous stage during a follow-up regeneration step. Our results consistently demonstrate RG-GAN’s robust performance across a variety of scenarios, including different GAN architectures, datasets, and degrees of data scarcity, reinforcing its value as a generic training methodology. Results also show that data augmentation exhibits improved performance in conjunction with RG-GAN. Furthermore, RG-GAN can achieve fewer parameters without compromising, and even enhancing, the quality of the generated samples. Code can be found at this link: https://github.com/IntellicentAI-Lab/RG-GAN

Content not yet available

Learning Optimal Advantage from Preferences and Mistaking It for Reward

Downloads

Next from AAAI 2024

Discovering Sequential Patterns with Predictable Inter-event Delays

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Content not yet available

Learning Optimal Advantage from Preferences and Mistaking It for Reward

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAAI 2024

Discovering Sequential Patterns with Predictable Inter-event Delays

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads