One of the dominant narratives of the deep learning renaissance has been the value of well-designed inductive bias - structural choices that shape what a model learns. The biggest example of this can be found in convolutional networks, where models achieve a dramatic parameter reduction by having features maps learn local patterns, which can then be re-used across the whole image. This is based on the prior belief that patterns in local images are generally locally contiguous, and so having feature maps that focus only on small (and gradually larger) local areas is a good fit for that prior. This paper operates in a similar spirit, except its input data isn’t in the form of an image, but a graph: the social graph of multiple agents operating within a Multi Agent RL Setting. In some sense, a graph is just a more general form of a pixel image: where a pixel within an image has a fixed number of neighbors, which have fixed discrete relationships to it (up, down, left, right), nodes within graphs have an arbitrary number of nodes, which can have arbitrary numbers and types of attributes attached to that relationship. 

The authors of this paper use graph networks as a sort of auxiliary information processing system alongside a more typical policy learning framework, on tasks that require group coordination and knowledge sharing to complete successfully. For example, each agent might be rewarded based on the aggregate reward of all agents together, and, in the stag hunt, it might require collaborative effort by multiple agents to successfully “capture” a reward. Because of this, you might imagine that it would be valuable to be able to predict what other agents within the game are going to do under certain circumstances, so that you can shape your strategy accordingly. 

The graph network used in this model represents both agents and objects in the environment as nodes, which have attributes including their position, whether they’re available or not (for capture-able objects), and what their last action was. As best I can tell, all agents start out with directed connections going both ways to all other agents, and to all objects in the environment, with the only edge attribute being whether the players are on the same team, for competitive environments. Given this setup, the graph network works through a sort of “diffusion” of information, analogous to a message passing algorithm. At each iteration (analogous to a layer), the edge features pull in information from their past value and sender and receiver nodes, as well as from a “global feature”. Then, all of the nodes pull in information from their edges, and their own past value. Finally, this “global attribute” gets updated based on summations over the newly-updated node and edge information. (If you were predicting attributes that were graph-level attributes, this global attribute might be where you’d do that prediction. However, in this case, we’re just interested in predicting agent-level actions). 

https://i.imgur.com/luFlhfJ.png

All of this has the effect of explicitly modeling agents as entities that both have information, and have connections to other entities. One benefit the authors claim of this structure is that it allows them more interpretability: when they “play out” the values of their graph network, which they call a Relational Forward Model or RFM, they observe edge values for two agents go up if those agents are about to collaborate on an action, and observe edge values for an agent and an object go up before that object is captured. Because this information is carefully shaped and structured, it makes it easier for humans to understand, and, in the tests the authors ran, appears to also help agents do better in collaborative games.

https://i.imgur.com/BCKSmIb.png

While I find graph networks quite interesting, and multi-agent learning quite interesting, I’m a little more uncertain about the inherent “graphiness” of this problem, since there aren’t really meaningful inherent edges between agents.  One thing I am curious about here is how methods like these would work in situations of sparser graphs, or, places where the connectivity level between a node’s neighbors, and the average other node in the graph is more distinct. Here, every node is connected to every other node, so the explicit information localization function of graph networks is less pronounced. I might naively think that - to whatever extent the graph is designed in a way that captures information meaningful to the task - explicit graph methods would have an even greater comparative advantage in this setting. 

How can we learn causal relationships that explain data? We can learn from non-stationary distributions. If we experiment with different factorizations of relationships between variables we can observe which ones provide better sample complexity when adapting to distributional shift and therefore are likely to be causal.

If we consider the variables A and B we can factor them in two ways:

$P(A,B) = P(A)P(B|A)$ representing a causal graph like $A\rightarrow B$

$P(A,B) = P(A|B)P(B)$ representing a causal graph like $A \leftarrow B$

The idea is if we train a model with one of these structures; when adapting to a new shifted distribution of data it will take longer to adapt if the model does not have the correct inductive bias. For example let's say that the true relationship is $A$=Raining causes $B$=Open Umbrella (and not vice-versa). Changing the marginal probability of Raining (say because the weather changed) does not change the mechanism that relates $A$ and $B$ (captured by $P(B|A)$), but will have an impact on the marginal $P(B)$. 

So after this distributional shift the function that modeled $P(B|A)$ will not need to change because the relationship is the same.  Only the function that modeled $P(A)$ will need to change. Under the incorrect factorization $P(B)P(A|B)$, adaptation to the change will be slow because both $P(B)$ and $P(A|B)$ need to be modified to account for the change in $P(A)$ (due to Bayes rule).

Here a difference in sample complexity can be observed when modeling the joint of the shifted distribution.  $B\rightarrow A$ takes longer to adapt:
https://i.imgur.com/B9FEmA7.png

Here the idea is that sample complexity when adapting to a new distribution of data is a heuristic to inform us which causal graph inductive bias is correct.

Experimentally this works and they also observe that when models have more capacity it seems that the difference between the models grows.

This summary was written with the help of Yoshua Bengio.

[Machine learning is a nuanced, complicated, intellectually serious topic...but sometimes it’s refreshing to let ourselves be a bit less serious, especially when it’s accompanied by clear, cogent writing on a topic. This particular is a particularly delightful example of good-natured silliness - from the dataset name HellaSwag to figures containing cartoons of BERT and ELMO representing language models - combined with interesting science.] 

https://i.imgur.com/CoSeh51.png

This paper tackles the problem of natural language comprehension, which asks: okay, our models can generate plausible looking text, but do they actually exhibit what we would consider true understanding of language? One natural structure of task for this is to take questions or “contexts”, and, given a set of possible endings or completion, pick the correct one. Positive examples are relatively easy to come by: adjacent video captions and question/answer pairs from WikiHow are two datasets used in this paper. However, it’s more difficult to come up with *negative* examples. Even though our incorrect endings won’t be a meaningful continuation of the sentence, we want them to be “close enough” that we can feel comfortable attributing a model’s ability to pick the correct answer as evidence of some meaningful kind of comprehension. As an obvious failure mode, if the alternative multiple choice options were all the same word repeated ten times, that would be recognizable as being not real language, and it would be easy for a model to select the answer with the distributional statistics of real language, but it wouldn’t prove much. Typically failure modes aren’t this egregious, but the overall intuition still holds, and will inform the rest of the paper: your ability to test comprehension on a given dataset is a function of how contextually-relevant and realistic your negative examples are.

Previous work (by many of the same authors as are on this paper), proposed a technique called Adversarial Filtering to try to solve this problem. In Adversarial Filtering, a generative language model is used to generate possible many endings conditioned on the input context, to be used as negative examples. Then, a discriminator is trained to predict the correct ending given the context. The generated samples that the discriminator had the highest confidence classifying as negative are deemed to be not challenging enough comparisons, and they’re thrown out and replaced with others from our pool of initially-generated samples. Eventually, once we’ve iterated through this process, we have a dataset with hopefully realistic negative examples. The negative examples are then given to humans to ensure none of them are conceptually meaningful actual endings to the sentence. The dataset released by the earlier paper, which used as it’s generator a relatively simple LSTM model, was called Swag. 

However, the authors came to notice that the performance of new language models (most centrally BERT) on this dataset might not be quite what it appears: its success rate of 86% only goes down to 76% if you don’t give the classifier access to the input context, which means it can get 76% (off of a random baseline of 25%, with 4 options) simply by evaluating which endings are coherent as standalone bits of natural language, without actually having to understand or even see the context. Also, shuffling the words in the words in the possible endings had a similarly small effect: the authors are able to get BERT to perform at 60% accuracy on the SWAG dataset with no context, and with shuffled words in the possible answers, meaning it’s purely selecting based on the distribution of words in the answer, rather than on the meaningfully-ordered sequence of words. 

https://i.imgur.com/f6vqJWT.png

The authors overall conclusion with this is: this adversarial filtering method is only as good as the generator, and, more specifically, the training dynamic between the generator that produces candidate endings, and the discriminator that filters them. If the generator is too weak, the negative examples can be easily detected as fake by a stronger model, but if the generator is too strong, then the discriminator can’t get good enough to usefully contribute by weeding samples out. They demonstrate this by creating a new version of Swag, which they call HellaSwag (for the expected acronym-optimization reasons), with a GPT generator rather than the simpler one used before: on this new dataset, all existing models get relatively poor results (30-40% performance). However, the authors’ overall point wasn’t “we’ve solved it, this new dataset is the end of the line,” but rather a call in the future to be wary, and generally aware that with benchmarks like these, especially with generated negative examples, it’s going to be a constantly moving target as generation systems get better. 

The goal of this work is to edit the model’s weights given new edit pairs ($x_e, y_e$) at test time. They achieve this by learning a "model editor network" that takes a fine tuning gradient computed from ($x_e, y_e$) and transforms this into a weight update. 

$$ f(\nabla W_l) \rightarrow \tilde\nabla W_l$$ 

The editor network is parameterized by the layer that it is predicting using a FiLM style scale and shift.

The editor network is trained on a small set of examples ($D^{tr}_{edit}$). The paper states that this dataset contains edits that are similar to the "the types of edits that will be made." which is interesting because it introduces generalization limitations to the potential edits.

An extra loss term is used to prevent unintended changes for other inputs to the model (called $x_{loc}$). This is achieved with the following loss that will maintain the predictions to be the same value.
$$L_{loc} = KL(p_{\theta_W}(\cdot | x_{loc}) \| p_{\theta_\tilde{W}}(\cdot | x_{loc}))$$
 

Some intuition for why this works is editor network $f$ approximates full dataset gradient from just a single example so it is more efficient. It can reduce the change of elements of the weight matrix which were disruptive to the loss when it was trained, information that requires many training examples to uncover.

This paper presents an end-to-end version of memory networks (Weston et al., 2015) such that the model doesn't train on the intermediate 'supporting facts' strong supervision of which input sentences are the best memory accesses, making it much more realistic. They also have multiple hops (computational steps) per output symbol. The tasks are Q&A and language modeling, and achieves strong results.

The paper is a useful extension of memNN because it removes the strong, unrealistic supervision requirement and still performs pretty competitively. The architecture is defined pretty cleanly and simply. The related work section is quite well-written, detailing the various similarities and differences with multiple streams of related work. The discussion about the model's connection to RNNs is also useful.